diff --git a/.github/workflows/is-deploy.yml b/.github/workflows/is-deploy.yml deleted file mode 100644 index 4d83d699..00000000 --- a/.github/workflows/is-deploy.yml +++ /dev/null @@ -1,18 +0,0 @@ -name: Build and deploy Jekyll site to GitHub Pages (IS) - -on: - push: - branches: - - main - -jobs: - github-pages: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v2 - - - uses: helaili/jekyll-action@v2 - with: - token: ${{ secrets.GITHUB_TOKEN }} - target_branch: 'gh-pages' - pre_build_commands: git config --global http.version HTTP/1.1; git config --global http.postBuffer 157286400; apk fetch git-lfs diff --git a/.github/workflows/jekyll.yml b/.github/workflows/jekyll.yml new file mode 100644 index 00000000..bd3b63af --- /dev/null +++ b/.github/workflows/jekyll.yml @@ -0,0 +1,47 @@ +name: Deploy Intelligent Systems Website to Pages + +on: + push: + branches: ["main"] + workflow_dispatch: + +permissions: + contents: read + pages: write + id-token: write + +concurrency: + group: "pages" + cancel-in-progress: false + +jobs: + build: + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + - name: Setup Ruby + uses: ruby/setup-ruby@v1 + with: + ruby-version: "3.1" + bundler-cache: true + - name: Setup Pages + id: pages + uses: actions/configure-pages@v5 + - name: Build with Jekyll + run: bundle exec jekyll build --baseurl "${{ steps.pages.outputs.base_path }}" + env: + JEKYLL_ENV: production + - name: Upload artifact + uses: actions/upload-pages-artifact@v3 + + deploy: + environment: + name: github-pages + url: ${{ steps.deployment.outputs.page_url }} + runs-on: ubuntu-latest + needs: build + steps: + - name: Deploy to GitHub Pages + id: deployment + uses: actions/deploy-pages@v4 diff --git a/.github/workflows/pages-deploy.yml b/.github/workflows/pages-deploy.yml deleted file mode 100755 index ece3ae31..00000000 --- a/.github/workflows/pages-deploy.yml +++ /dev/null @@ -1,17 +0,0 @@ -name: Build and deploy Jekyll site to GitHub Pages - -on: - push: - branches: - - master - -jobs: - github-pages: - runs-on: ubuntu-latest - steps: - - uses: actions/checkout@v2 - - - uses: helaili/jekyll-action@v2 - with: - token: ${{ secrets.GITHUB_TOKEN }} - target_branch: 'gh-pages' diff --git a/.gitignore b/.gitignore index 5509140f..2ba89e9a 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1,6 @@ *.DS_Store +_site/ +.sass-cache/ +.jekyll-cache/ +.jekyll-metadata +Gemfile.lock diff --git a/Gemfile b/Gemfile index 9478cde8..5b2b0161 100755 --- a/Gemfile +++ b/Gemfile @@ -3,8 +3,11 @@ gem 'ffi', '= 1.16.3' gem 'jekyll', '~> 3.9' gem 'coderay', '~> 1.1.3' gem 'jekyll-toc', '~> 0.17.1' +gem 'bigdecimal' gem 'kramdown-parser-gfm' gem 'jekyll-sitemap' +gem "base64" +gem "logger" group :jekyll_plugins do gem 'jekyll-asciidoc', '~> 2.1.1' diff --git a/README.md b/README.md index 54998cc9..a5709fde 100755 --- a/README.md +++ b/README.md @@ -1,65 +1,43 @@ -# Machine Learning Phystech WebSite +# Intelligent Systems Department Website -**Если вы значительно меняете сайт (добавляете страницы и т.п.), рекомендуется перед коммитом проверить работоспособность сайта:** -`sudo bash docker_test.sh` - -## Добавление курса: TODO --- сейчас не актуально -Для добавления нового курса требуется создать файл `course_name.md` в папке `_course/`. Далее требуется заполнить метаинформацию о курсе: -``` ---- -title: Сюда вписать названия курса (название которое во вкладке браузера ) -name: Продублировать название курса (название которое будет на сайте) -type: bachelor (курс из бакалавриата или магистратуры, валидные поля bachelor/master) -avatar: название изображению в папке images/course (если поле пустое, то будет взято default.jpg изображение) -lecturers: лекторы через запятую, в качестве идентификатора использовать название файлов (без приставки .md) в папке _people (например strijov_vv,grabovoy_av) -site: основной сайт курса (можно не указывать), ВАЖНО! Без приставки https:// ---- -``` +[![License](https://badgen.net/github/license/intsystems/intsystems.github.io)](https://github.com/intsystems/intsystems.github.io/blob/main/LICENSE) +[![GitHub Contributors](https://img.shields.io/github/contributors/intsystems/intsystems.github.io)](https://github.com/intsystems/intsystems.github.io/graphs/contributors) -После заполенения метаинформации требуется указать описание самого курса в формате markdown. +This repository contains the source code for the Intelligent Systems Department website. It is designed to provide information about our department, courses, lecturers, research, publications and contact details. -## Добавление пользователя: TODO --- сейчас не актуально -Для добавления нового пользователя требуется создать файл `lecturer_name.md` в папке `_people/`. Далее требуется заполнить метаинформацию о лекторе: -``` ---- -title: Сюда вписать имя фамилию преподавателя (название которое во вкладке браузера ) -name: Продублировать имя преподавателя (так как на сайте будет) -position: phd (начная степень преподавателя или должность, возможные значения смотрите тут https://github.com/intsystems/intsystems.github.ioblob/master/_config.yml#L81) -avatar: название изображению в папке images/people (если поле пустое, то будет взято default.jpg изображение) -mail: почта преподавателя (может быть пусто) -site: сайт преподавателя (может быть пусто) -scholar: ссылка на scholar (может быть пусто) ---- -``` +If you want to make a large contribution, please do it in a pull request, and ask [@kisnikser](https://github.com/kisnikser) for a review. Else if your changes are small (typos, small content edits), you can directly edit the files in GitHub web interface as follows. -Вся дополнительная информация указывается ниже в формате markdown. +## Research Report -## Исправления текста локализации en/ru +1. Go to the file [`_i18n/en/nir.md`](_i18n/en/nir.md). +2. If you add new semester, create a new section, e.g., `### 2025 Fall`, and create a table for your course (see previous semesters for examples). +3. Add your report information in the format: + ```markdown + | Student | Topic | Advisor | Links | + | :----------- | :--------- | :-------------------- | :--------------------------------------- | + | Name Surname | Topic name | Name Surname, PhD/DSc | [Paper](URL), [Code](URL), [Slides](URL) | + ``` -Английский язык: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/en.yml) +## Thesis -Русский язык: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/ru.yml) +1. Go to the file [`_i18n/en/thesis.md`](_i18n/en/thesis.md). +2. If you add new year, create a new section, e.g., `### 2025`, and create a table for your course (see previous years for examples). +3. Add your report information in the format: + ```markdown + | Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | + | :----------- | :---------- | :-------------------- | :-------------- | ------------- | -------------- | + | Name Surname | Thesis name | Name Surname, PhD/DSc | [Project](URL) | [Thesis](URL) | [Slides](URL) | + ``` -## Изменения страницы HOME +## People -Метаинформация страницы: [ссылка](https://github.com/intsystems/intsystems.github.ioedit/master/index.md) +1. Create or edit a file in the [`_people`](_people/) folder. Use the existing files as a reference for the structure and required fields. Each file should be named using the format `lastname_firstname.md`. +2. Add a brief biography and any relevant links (e.g., personal website, scholar, elibrary) to the files in [`_i18n/en/_people/`](_i18n/en/_people/) and [`_i18n/ru/_people/`](_i18n/ru/_people/) directories. Name files consistently across languages, following the same `lastname_firstname` format. +3. Add the person's profile picture to the [`images/people/`](images/people/) folder. Please, compress the image to optimize loading times. Add image filename to the file from 1st step. +4. Update meta information `people` in the [`_i18n/en.yml`](_i18n/en.yml) and [`_i18n/ru.yml`](_i18n/ru.yml) files to include the new person, following the same `lastname_firstname` format. -Английская версия: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/en/index.md) +## Courses -Русская версия: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/ru/index.md) - -## Изменения страницы ABOUT - -Метаинформация страницы: [ссылка](https://github.com/intsystems/intsystems.github.ioedit/master/about.md) - -Английская версия: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/en/about.md) - -Русская версия: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/ru/about.md) - -## Изменения страницы Admission - -Метаинформация страницы: [ссылка](https://github.com/intsystems/intsystems.github.ioedit/master/admission.md) - -Английская версия: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/en/admission.md) - -Русская версия: [ссылка](https://github.com/intsystems/intsystems.github.ioblob/master/_i18n/ru/admission.md) +1. Create or edit a file in the [`_course`](_course/) folder. Use the existing files as a reference for the structure and required fields. Each file should be named using the format `course_name.md`. +2. Add course details and any relevant links (e.g., syllabus, resources) to the files in [`_i18n/en/_course/`](_i18n/en/_course/) and [`_i18n/ru/_course/`](_i18n/ru/_course/) directories. Name files consistently across languages, following the same `course_name` format. +3. Update meta information `courses` in the [`_i18n/en.yml`](_i18n/en.yml) and [`_i18n/ru.yml`](_i18n/ru.yml) files to include the new course, following the same `course_name` format. diff --git a/_config.yml b/_config.yml index c5a95020..2d9299d8 100755 --- a/_config.yml +++ b/_config.yml @@ -1,14 +1,13 @@ -brand: /images/logo/logo_square.jpg +brand: /images/logo/logo-square.png +logo: /images/logo/logo-full.png image: og: - image: /images/main/main.jpg + image: /images/main/main.jpg -url: https://intsystems.github.io -edit: https://github.com/intsystems/intsystems.github.io/edit/main/ -baseurl: -permalink: /:year/:month/:day/:title.html - -sidebar: true +url: https://kisnikser.github.io +edit: https://github.com/kisnikser/intsystems.github.io/edit/main/ +baseurl: /intsystems.github.io +permalink: /:year/:month/:day/:title.html # Main Info github: intsystems @@ -18,87 +17,80 @@ telegram: https://t.me/IS_MIPT rutube: https://rutube.ru/channel/40144363 header: -- Machine Learning -- Data Analysis + - Machine Learning + - Data Analysis # Markdown -markdown: kramdown +markdown: kramdown # Sass sass: - sass_dir: _sass - style: :compressed + sass_dir: _sass + style: :compressed exclude: ["LICENSE", "README.md", "Gemfile", "Gemfile.lock", "vendor", "_sass"] # Highlighter -highlighter: rouge +highlighter: rouge plugins: - - jekyll-feed - jekyll-multiple-languages-plugin - - jekyll-toc - - jekyll-sitemap languages: ["en", "ru"] -exclude_from_localizations: ["images", "favicon.ico", "javascript", "style.scss"] +exclude_from_localizations: + ["images", "favicon.ico", "javascript", "style.scss"] default_locale_in_subfolder: False # Navigation nav: pages: - - id: "home" - href: "/" - name: site.nav.names.home - - id: "education" - href: "/education" - name: site.nav.names.education - - id: "about" - href: "/about" - name: site.nav.names.about - - id: "lecturers" - href: "/people" - name: site.nav.names.lecturers - - id: "courses" - href: "/course" - name: site.nav.names.courses - - id: "admission" - href: "/admission" - name: site.nav.names.admission - - id: "materials" - href: "/materials" - name: site.nav.names.materials - dropdown: - - id: "nir" - href: "/materials/nir" - name: site.nav.names.nir - - id: "scholarship" - href: "/materials/scholarship" - name: site.nav.names.scholarship - - id: "conferences" - href: "/materials/conferences" - name: site.nav.names.conferences - - id: "thesis" - href: "/materials/thesis" - name: site.nav.names.thesis - - id: "seminars" - href: "/materials/seminars" - name: site.nav.names.seminars - - id: "paper_guidelines" - href: "/materials/paper_guidelines" - name: site.nav.names.paper_guidelines + - id: "home" + href: "/" + name: site.nav.names.home + - id: "education" + href: "/education" + name: site.nav.names.education + - id: "lecturers" + href: "/people" + name: site.nav.names.lecturers + - id: "courses" + href: "/course" + name: site.nav.names.courses + - id: "admission" + href: "/admission" + name: site.nav.names.admission + - id: "materials" + href: "/materials" + name: site.nav.names.materials + dropdown: + - id: "nir" + href: "/materials/nir" + name: site.nav.names.nir + - id: "thesis" + href: "/materials/thesis" + name: site.nav.names.thesis + - id: "seminars" + href: "/materials/seminars" + name: site.nav.names.seminars + - id: "scholarship" + href: "/materials/scholarship" + name: site.nav.names.scholarship + - id: "paper_guidelines" + href: "/materials/paper_guidelines" + name: site.nav.names.paper_guidelines + - id: "templates" + href: "/materials/templates" + name: site.nav.names.templates + - id: "conferences" + href: "/materials/conferences" + name: site.nav.names.conferences # Scopes defaults: - scope: path: "" - values: - toc: true - - scope: - path: "" - type: "pages" values: layout: "page" - scope: @@ -130,22 +122,23 @@ collections: output: true permalink: /course/:title/index.html - global: langs: - ru: Русский - en: English + ru: RU + en: EN course: types: - - bachelor - - master - - deprecated + - bachelor + - master + - deprecated + - draft people: roles: - - hotd - - dos - - phd - - gs - - template + - hotd + - dos + - phd + - pgs + - gs + - template diff --git a/_course/automation_scientific_research.md b/_course/automation_scientific_research.md index 3481b86c..48e77a44 100755 --- a/_course/automation_scientific_research.md +++ b/_course/automation_scientific_research.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.automation_scientific_research -name: courses.name +title: courses.automation_scientific_research type: bachelor -avatar: -lecturers: strijov_vv -site: +lecturers: dorin_dd,grabovoy_av,bakhteev_oy,strijov_vv +site: https://github.com/intsystems/m1p --- -{% tf _course/automation_scientific_research.md %} \ No newline at end of file +{% tf _course/automation_scientific_research.md %} diff --git a/_course/bayesian_model_selection.md b/_course/bayesian_model_selection.md index a1aacbe1..77e52e99 100755 --- a/_course/bayesian_model_selection.md +++ b/_course/bayesian_model_selection.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.bayesian_model_selection -name: courses.name +title: courses.bayesian_model_selection type: bachelor -avatar: -lecturers: aduenko_aa -site: +lecturers: aduenko_aa,yakovlev_kd +site: http://www.machinelearning.ru/wiki/index.php?title=%D0%91%D0%B0%D0%B9%D0%B5%D1%81%D0%BE%D0%B2%D1%81%D0%BA%D0%B8%D0%B9_%D0%B2%D1%8B%D0%B1%D0%BE%D1%80_%D0%BC%D0%BE%D0%B4%D0%B5%D0%BB%D0%B5%D0%B9_%28%D1%82%D0%B5%D0%BE%D1%80%D0%B8%D1%8F_%D0%B8_%D0%BF%D1%80%D0%B0%D0%BA%D1%82%D0%B8%D0%BA%D0%B0%2C_%D0%90.%D0%90._%D0%90%D0%B4%D1%83%D0%B5%D0%BD%D0%BA%D0%BE%2C_%D0%9A.%D0%94._%D0%AF%D0%BA%D0%BE%D0%B2%D0%BB%D0%B5%D0%B2%2C_%D0%92.%D0%92._%D0%A1%D1%82%D1%80%D0%B8%D0%B6%D0%BE%D0%B2%29/%D0%93%D1%80%D1%83%D0%BF%D0%BF%D0%B0_274%2C_%D0%BE%D1%81%D0%B5%D0%BD%D1%8C_2025 --- -{% tf _course/bayesian_model_selection.md %} \ No newline at end of file +{% tf _course/bayesian_model_selection.md %} diff --git a/_course/bayesian_multimodeling.md b/_course/bayesian_multimodeling.md index 153d3c0e..c0a3e67c 100755 --- a/_course/bayesian_multimodeling.md +++ b/_course/bayesian_multimodeling.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.bayesian_multimodeling -name: courses.name +title: courses.bayesian_multimodeling type: master -avatar: lecturers: bakhteev_oy -site: +site: https://github.com/intsystems/BMM --- -{% tf _course/bayesian_multimodeling.md %} \ No newline at end of file +{% tf _course/bayesian_multimodeling.md %} diff --git a/_course/bioinformatics.md b/_course/bioinformatics.md index 144a7af5..8e46a30f 100755 --- a/_course/bioinformatics.md +++ b/_course/bioinformatics.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.bioinformatics -name: courses.name +title: courses.bioinformatics type: master -avatar: lecturers: torshin_iy -site: +site: http://www.machinelearning.ru/wiki/index.php?title=%D0%91%D0%B8%D0%BE%D0%B8%D0%BD%D1%84%D0%BE%D1%80%D0%BC%D0%B0%D1%82%D0%B8%D0%BA%D0%B0_%D0%B8_%D0%B7%D0%B0%D0%B4%D0%B0%D1%87%D0%B8_%D1%80%D0%B0%D1%81%D0%BF%D0%BE%D0%B7%D0%BD%D0%B0%D0%B2%D0%B0%D0%BD%D0%B8%D1%8F_%D0%B2_%D1%81%D0%BE%D0%B2%D1%80%D0%B5%D0%BC%D0%B5%D0%BD%D0%BD%D0%BE%D0%B9_%D0%B1%D0%B8%D0%BE%D0%BB%D0%BE%D0%B3%D0%B8%D0%B8_%28%D0%BA%D1%83%D1%80%D1%81_%D0%BB%D0%B5%D0%BA%D1%86%D0%B8%D0%B9%2C_%D0%98.%D0%AE._%D0%A2%D0%BE%D1%80%D1%88%D0%B8%D0%BD%29 --- -{% tf _course/bioinformatics.md %} \ No newline at end of file +{% tf _course/bioinformatics.md %} diff --git a/_course/computational_geometry.md b/_course/computational_geometry.md index 00112c5e..3a1db108 100755 --- a/_course/computational_geometry.md +++ b/_course/computational_geometry.md @@ -1,9 +1,6 @@ --- -edit: true -title: courses.title.computational_geometry -name: courses.name +title: courses.computational_geometry type: deprecated -avatar: lecturers: mestetskiy_lm site: --- diff --git a/_course/computer_vision.md b/_course/computer_vision.md new file mode 100644 index 00000000..8cd1bd44 --- /dev/null +++ b/_course/computer_vision.md @@ -0,0 +1,8 @@ +--- +title: courses.computer_vision +type: draft +lecturers: dorin_dd,kiselev_ns,kreinin_mv,nikitina_ma +site: https://github.com/intsystems/computer-vision +--- + +{% tf _course/computer_vision.md %} diff --git a/_course/deep_generative_models.md b/_course/deep_generative_models.md index 9b552508..421517cf 100755 --- a/_course/deep_generative_models.md +++ b/_course/deep_generative_models.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.deep_generative_models -name: courses.name +title: courses.deep_generative_models type: master -avatar: -lecturers: isachenko_rv,mokrov_pv -site: https://github.com/r-isachenko/2023-DGM-MIPT-course +lecturers: isachenko_rv,morozov_ma +site: https://github.com/r-isachenko/2025-DGM-MIPT-YSDA-course --- {% tf _course/deep_generative_models.md %} diff --git a/_course/deep_learning.md b/_course/deep_learning.md index 2124b458..b876b1af 100755 --- a/_course/deep_learning.md +++ b/_course/deep_learning.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.deep_learning -name: courses.name +title: courses.deep_learning type: bachelor -avatar: -lecturers: kropotov_da,grebenkova_os,filatov_av,bishuk_ay,yakovlev_kd -site: +lecturers: vladimirov_ea,dorin_dd,kiselev_ns,firsov_sa,kasyuk_va +site: https://github.com/intsystems/Deep-Learning-Course --- {% tf _course/deep_learning.md %} diff --git a/_course/deep_learning_audio.md b/_course/deep_learning_audio.md new file mode 100755 index 00000000..912bb0fc --- /dev/null +++ b/_course/deep_learning_audio.md @@ -0,0 +1,8 @@ +--- +title: courses.deep_learning_audio +type: master +lecturers: severilov_pa +site: https://github.com/severilov/DL-Audio-Course +--- + +{% tf _course/deep_learning_audio.md %} diff --git a/_course/forecasting_methods.md b/_course/forecasting_methods.md index abb272b9..641395d2 100755 --- a/_course/forecasting_methods.md +++ b/_course/forecasting_methods.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.forecasting_methods -name: courses.name +title: courses.forecasting_methods type: bachelor -avatar: -lecturers: strijov_vv,samokhina_am,tikhonov_dm -site: +lecturers: tikhonov_dm,panchenko_sk +site: https://github.com/intsystems/MathematicalForecastingMethods --- {% tf _course/forecasting_methods.md %} diff --git a/_course/functional_data_analysis.md b/_course/functional_data_analysis.md new file mode 100755 index 00000000..b8602ea0 --- /dev/null +++ b/_course/functional_data_analysis.md @@ -0,0 +1,8 @@ +--- +title: courses.functional_data_analysis +type: master +lecturers: strijov_vv +site: https://m1p.org/index.php/Functional_Data_Analysis +--- + +{% tf _course/functional_data_analysis.md %} diff --git a/_course/fundamental_ml_theorems.md b/_course/fundamental_ml_theorems.md index fc100e76..d8918681 100644 --- a/_course/fundamental_ml_theorems.md +++ b/_course/fundamental_ml_theorems.md @@ -1,9 +1,6 @@ --- -edit: true -title: courses.title.fundamental_ml_theorems -name: courses.name +title: courses.fundamental_ml_theorems type: deprecated -avatar: lecturers: strijov_vv site: --- diff --git a/_course/image_processing_recognition.md b/_course/image_processing_recognition.md index 9c6200b0..143cda08 100755 --- a/_course/image_processing_recognition.md +++ b/_course/image_processing_recognition.md @@ -1,9 +1,6 @@ --- -edit: true -title: courses.title.image_processing_recognition -name: courses.name +title: courses.image_processing_recognition type: deprecated -avatar: lecturers: mestetskiy_lm site: --- diff --git a/_course/intellectual_data_analysis.md b/_course/intellectual_data_analysis.md index 28a54509..eb110e2f 100755 --- a/_course/intellectual_data_analysis.md +++ b/_course/intellectual_data_analysis.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.intellectual_data_analysis -name: courses.name +title: courses.intellectual_data_analysis type: master -avatar: -lecturers: strijov_vv,bakhteev_oy -site: +lecturers: strijov_vv,vladimirov_ea +site: https://github.com/intsystems/ida --- {% tf _course/intellectual_data_analysis.md %} diff --git a/_course/introduction_machine_learning.md b/_course/introduction_machine_learning.md index 8bf66264..11a2add4 100755 --- a/_course/introduction_machine_learning.md +++ b/_course/introduction_machine_learning.md @@ -1,9 +1,6 @@ --- -edit: true -title: courses.title.introduction_machine_learning -name: courses.name +title: courses.introduction_machine_learning type: bachelor -avatar: lecturers: vorontsov_kv site: http://www.machinelearning.ru/wiki/index.php?title=Машинное_обучение_%28курс_лекций%2C_К.В.Воронцов%29 --- diff --git a/_course/natural_language_processing.md b/_course/natural_language_processing.md index ee03d6b2..9fc1370b 100755 --- a/_course/natural_language_processing.md +++ b/_course/natural_language_processing.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.natural_language_processing -name: courses.name -type: master -avatar: +title: courses.natural_language_processing +type: deprecated lecturers: popov_as,hrilchenkov_ky -site: +site: --- -{% tf _course/natural_language_processing.md %} \ No newline at end of file +{% tf _course/natural_language_processing.md %} diff --git a/_course/networks_text_analysis.md b/_course/networks_text_analysis.md index f0f2504e..2d0148fb 100755 --- a/_course/networks_text_analysis.md +++ b/_course/networks_text_analysis.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.networks_text_analysis -name: courses.name -type: bachelor -avatar: +title: courses.networks_text_analysis +type: deprecated lecturers: meysuradze_ai -site: +site: --- -{% tf _course/networks_text_analysis.md %} \ No newline at end of file +{% tf _course/networks_text_analysis.md %} diff --git a/_course/neural_architecture_search.md b/_course/neural_architecture_search.md index 0acca041..bf1dfe2a 100644 --- a/_course/neural_architecture_search.md +++ b/_course/neural_architecture_search.md @@ -1,9 +1,6 @@ --- -edit: true -title: courses.title.neural_architecture_search -name: courses.name +title: courses.neural_architecture_search type: deprecated -avatar: lecturers: potanin_ms site: --- diff --git a/_course/optimization_methods.md b/_course/optimization_methods.md deleted file mode 100644 index a1803938..00000000 --- a/_course/optimization_methods.md +++ /dev/null @@ -1,11 +0,0 @@ ---- -edit: true -title: courses.title.optimization_methods -name: courses.name -type: bachelor -avatar: -lecturers: beznosikov_an -site: ---- - -{% tf _course/optimization_methods.md %} diff --git a/_course/probabilistic_topic_models.md b/_course/probabilistic_topic_models.md index 6af132dc..19863e22 100755 --- a/_course/probabilistic_topic_models.md +++ b/_course/probabilistic_topic_models.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.probabilistic_topic_models -name: courses.name +title: courses.probabilistic_topic_models type: master -avatar: lecturers: vorontsov_kv -site: +site: http://bit.ly/2EGWcjA --- -{% tf _course/probabilistic_topic_models.md %} \ No newline at end of file +{% tf _course/probabilistic_topic_models.md %} diff --git a/_course/programming_practicum_python.md b/_course/programming_practicum_python.md new file mode 100755 index 00000000..7ad78878 --- /dev/null +++ b/_course/programming_practicum_python.md @@ -0,0 +1,8 @@ +--- +title: courses.programming_practicum_python +type: bachelor +lecturers: apishev_ma +site: https://github.com/MelLain/mipt-python +--- + +{% tf _course/programming_practicum_python.md %} diff --git a/_course/recommender_systems.md b/_course/recommender_systems.md index 71b9cb51..6e6548ef 100644 --- a/_course/recommender_systems.md +++ b/_course/recommender_systems.md @@ -1,9 +1,6 @@ --- -edit: true -title: courses.title.recommender_systems -name: courses.name +title: courses.recommender_systems type: bachelor -avatar: lecturers: grishanov_av,volodkevich_aa site: https://github.com/shashist/recsys-course --- diff --git a/_course/rnd_in_ai.md b/_course/rnd_in_ai.md index cb749d15..4f335fb5 100755 --- a/_course/rnd_in_ai.md +++ b/_course/rnd_in_ai.md @@ -1,9 +1,6 @@ --- -edit: true -title: courses.title.rnd_in_ai -name: courses.name -type: master -avatar: +title: courses.rnd_in_ai +type: bachelor,master lecturers: grabovoy_av site: https://github.com/Intelligent-Systems-Phystech/CreationOfIntelligentSystems --- diff --git a/_course/signal_processing.md b/_course/signal_processing.md index 712e059b..5b7b6251 100755 --- a/_course/signal_processing.md +++ b/_course/signal_processing.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.signal_processing -name: courses.name -type: master -avatar: +title: courses.signal_processing +type: deprecated lecturers: strijov_vv -site: +site: --- -{% tf _course/signal_processing.md %} \ No newline at end of file +{% tf _course/signal_processing.md %} diff --git a/_course/software_engineering_data_analysis.md b/_course/software_engineering_data_analysis.md index 4e4e26a8..02840893 100755 --- a/_course/software_engineering_data_analysis.md +++ b/_course/software_engineering_data_analysis.md @@ -1,11 +1,8 @@ --- -edit: true -title: courses.title.software_engineering_data_analysis -name: courses.name -type: master -avatar: +title: courses.software_engineering_data_analysis +type: bachelor,master lecturers: khritankov_as -site: +site: --- -{% tf _course/software_engineering_data_analysis.md %} \ No newline at end of file +{% tf _course/software_engineering_data_analysis.md %} diff --git a/_data/conferences.yml b/_data/conferences.yml new file mode 100644 index 00000000..d07cb3c4 --- /dev/null +++ b/_data/conferences.yml @@ -0,0 +1,109 @@ +conferences: + - name: "NeurIPS" + full_name: "Neural Information Processing Systems" + submission_deadline: "2025-05-21" + conference_date: "2025-12-09" + location: "Vancouver, Canada" + website: "https://neurips.cc" + rank: "A*" + active: false + + - name: "ICML" + full_name: "International Conference on Machine Learning" + submission_deadline: "2026-01-31" + conference_date: "2026-07-12" + location: "TBA" + website: "https://icml.cc" + rank: "A*" + active: false + + - name: "ICLR" + full_name: "International Conference on Learning Representations" + submission_deadline: "2025-10-01" + conference_date: "2026-04-24" + location: "Singapore" + website: "https://iclr.cc" + rank: "A*" + active: false + + - name: "CVPR" + full_name: "Conference on Computer Vision and Pattern Recognition" + submission_deadline: "2025-11-15" + conference_date: "2026-06-16" + location: "Seattle, USA" + website: "https://cvpr.thecvf.com" + rank: "A*" + active: false + + - name: "ICCV" + full_name: "International Conference on Computer Vision" + abstract_deadline: "2026-03-01" + submission_deadline: "2026-03-15" + conference_date: "2026-10-10" + location: "TBA" + website: "http://iccv2026.thecvf.com" + rank: "A*" + active: false + + - name: "ECCV" + full_name: "European Conference on Computer Vision" + submission_deadline: "2026-03-07" + conference_date: "2026-09-30" + location: "TBA" + website: "https://eccv2026.ecva.net" + rank: "A*" + active: false + + - name: "AAAI" + full_name: "AAAI Conference on Artificial Intelligence" + submission_deadline: "2025-08-07" + conference_date: "2026-02-23" + location: "Philadelphia, USA" + website: "https://aaai.org/conference/aaai/" + rank: "A*" + active: false + + - name: "IJCAI" + full_name: "International Joint Conference on Artificial Intelligence" + submission_deadline: "2026-01-21" + conference_date: "2026-08-21" + location: "TBA" + website: "https://www.ijcai.org" + rank: "A*" + active: false + + - name: "AISTATS" + full_name: "International Conference on Artificial Intelligence and Statistics" + submission_deadline: "2025-10-14" + conference_date: "2026-04-14" + location: "Valencia, Spain" + website: "http://aistats.org" + rank: "A" + active: false + + - name: "KDD" + full_name: "ACM SIGKDD Conference on Knowledge Discovery and Data Mining" + submission_deadline: "2026-02-06" + conference_date: "2026-08-23" + location: "TBA" + website: "https://www.kdd.org" + rank: "A*" + active: false + + - name: "ACL" + full_name: "Annual Meeting of the Association for Computational Linguistics" + submission_deadline: "2026-02-15" + conference_date: "2026-07-30" + location: "TBA" + website: "https://www.2026.aclweb.org" + rank: "A*" + active: false + + - name: "EMNLP" + full_name: "Conference on Empirical Methods in Natural Language Processing" + submission_deadline: "2025-06-15" + conference_date: "2025-11-12" + location: "Miami, USA" + website: "https://2025.emnlp.org" + rank: "A" + active: false diff --git a/_i18n/en.yml b/_i18n/en.yml index 3ad4dad0..8f32f808 100755 --- a/_i18n/en.yml +++ b/_i18n/en.yml @@ -1,172 +1,123 @@ site: index: department: |- - Department of Intelligent Systems + Intelligent Systems Department address: |- - Earth + Long Lake City - name: Intelligent Systems Phystech + name: Intelligent Systems nav: names: - home: home - about: about - lecturers: lecturers - courses: courses - admission: admission - materials: materials - nir: research reports - scholarship: scholarships - conferences: conferences list - thesis: theses - education: timetable - seminars: seminars - paper_guidelines: scientific paper writing + home: Home + education: Schedule + lecturers: People + courses: Courses + admission: Admission + materials: Materials + nir: Research Reports + thesis: Theses + seminars: Meetings + scholarship: Scholarships + paper_guidelines: Paper Guidelines + templates: Templates + conferences: Conferences & Journals + + toc: + title: Contents + toggle: Toggle table of contents global: course: types: bachelor: Bachelor master: Master - deprecated: No longer taught + deprecated: Archived + draft: Draft people: roles: hotd: Founders of the Department dos: Doctors of Science phd: PhD + pgs: Postgraduate Students gs: Graduate Students template: TEMPLATE - - -peoples: - name: - grabovoy_av: Andrey Grabovoy - aduenko_aa: Aleksander Aduenko - bakhteev_oy: Oleg Bakhteev - khrilchenko_ky: Kirill Khrylchenko - isachenko_rv: Roman Isachenko - khritankov_as: Anton Khritankov - kropotov_da: Dmitriy Kropotov - meysuradze_ai: Archil Meysuradze - mestetskiy_lm: Leonid Mestetskiy - popov_as: Artem Popov - potanin_ms: Mark Potanin - strijov_vv: Vadim Strijov - vorontsov_kv: Konstantin Vorontsov - torshin_iy: Ivan Torshin - rudakov_kv: Konstantin Rudakov - zhuravlyov_yv: Yuri Zhuravlyov - apishev_ma: Murat Apishev - gneushev_an: Alexander Gneushev - dulin_sk: Sergey Dulin - khoroshevsky_vf: Vladimir Khoroshevsky - mohonko_ez: Elena Mohonko - tsurkov_vi: Vladimir Tsurkov - matveev_ia: Ivan Matveev - chekhovich_yv: Yury Chekhovich - grebenkova_os: Olga Grebenkova - filatov_av: Andrey Filatov - samokhina_am: Alina Samokhina - severilov_pa: Pavel Severilov - tikhonov_dm: Denis Tikhonov - bishuk_ay: Anton Bishuk - grishanov_av: Alexey Grishanov - volodkevich_aa: Anna Volodkevich - beznosikov_an: Aleksandr Beznosikov - mokrov_pv: Petr Mokrov - yakovlev_kd: Konstantin Yakovlev - - title: - grabovoy_av: Andrey Grabovoy - aduenko_aa: Aleksander Aduenko - bakhteev_oy: Oleg Bakhteev - khrilchenko_ky: Kirill Khrylchenko - isachenko_rv: Roman Isachenko - khritankov_as: Anton Khritankov - kropotov_da: Dmitriy Kropotov - meysuradze_ai: Archil Meysuradze - mestetskiy_lm: Leonid Mestetskiy - popov_as: Artem Popov - potanin_ms: Mark Potanin - strijov_vv: Vadim Strijov - vorontsov_kv: Konstantin Vorontsov - torshin_iy: Ivan Torshin - rudakov_kv: Konstantin Rudakov - zhuravlyov_yv: Yuri Zhuravlyov - apishev_ma: Murat Apishev - gneushev_an: Alexander Gneushev - dulin_sk: Sergey Dulin - khoroshevsky_vf: Vladimir Khoroshevsky - mohonko_ez: Elena Mohonko - tsurkov_vi: Vladimir Tsurkov - matveev_ia: Ivan Matveev - chekhovich_yv: Yury Chekhovich - grebenkova_os: Olga Grebenkova - filatov_av: Andrey Filatov - samokhina_am: Alina Samokhina - severilov_pa: Pavel Severilov - tikhonov_dm: Denis Tikhonov - bishuk_ay: Anton Bishuk - grishanov_av: Alexey Grishanov - volodkevich_aa: Anna Volodkevich - beznosikov_an: Aleksandr Beznosikov - mokrov_pv: Petr Mokrov - yakovlev_kd: Konstantin Yakovlev - +people: + grabovoy_av: Andrey Grabovoy + aduenko_aa: Aleksander Aduenko + bakhteev_oy: Oleg Bakhteev + khrilchenko_ky: Kirill Khrylchenko + isachenko_rv: Roman Isachenko + khritankov_as: Anton Khritankov + kropotov_da: Dmitriy Kropotov + meysuradze_ai: Archil Meysuradze + mestetskiy_lm: Leonid Mestetskiy + popov_as: Artem Popov + potanin_ms: Mark Potanin + strijov_vv: Vadim Strijov + vorontsov_kv: Konstantin Vorontsov + torshin_iy: Ivan Torshin + rudakov_kv: Konstantin Rudakov + zhuravlyov_yv: Yuri Zhuravlyov + apishev_ma: Murat Apishev + gneushev_an: Alexander Gneushev + dulin_sk: Sergey Dulin + khoroshevsky_vf: Vladimir Khoroshevsky + mohonko_ez: Elena Mohonko + tsurkov_vi: Vladimir Tsurkov + matveev_ia: Ivan Matveev + chekhovich_yv: Yury Chekhovich + grebenkova_os: Olga Grebenkova + filatov_av: Andrey Filatov + samokhina_am: Alina Samokhina + severilov_pa: Pavel Severilov + tikhonov_dm: Denis Tikhonov + bishuk_ay: Anton Bishuk + grishanov_av: Alexey Grishanov + volodkevich_aa: Anna Volodkevich + mokrov_pv: Petr Mokrov + yakovlev_kd: Konstantin Yakovlev + panchenko_sk: Sviatoslav Panchenko + vladimirov_ea: Eduard Vladimirov + dorin_dd: Daniil Dorin + kiselev_ns: Nikita Kiselev + firsov_sa: Sergey Firsov + kasyuk_va: Vadim Kasyuk + morozov_ma: Matvey Morozov + kreinin_mv: Matvei Kreinin + nikitina_ma: Maria Nikitina courses: - name: - automation_scientific_research: Automation of Scientific Research - bayesian_model_selection: Bayesian Model Selection - bayesian_multimodeling: Bayesian Multimodeling - bioinformatics: Bioinformatics - computational_geometry: Computational Geometry - deep_generative_models: Deep Generative Models - deep_learning: Deep Learning - forecasting_methods: Forecasting Methods - fundamental_ml_theorems: Fundamental Machine Learning Theorems - image_processing_recognition: Image Processing and Recognition - introduction_machine_learning: Introduction to Machine Learning - natural_language_processing: Natural Language Processing - networks_text_analysis: Networks and Text Analysis - neural_architecture_search: Neural Architecture Search - probabilistic_topic_models: Probabilistic Topic Models - recommender_systems: Recommender Systems - rnd_in_ai: Creation of Intelligent Systems - signal_processing: Signal Processing - software_engineering_data_analysis: Software Engineering for Data Analysis - intellectual_data_analysis: Intellectual Data Analysis - optimization_methods: Optimization methods in Machine Learning - - title: - automation_scientific_research: Automation of Scientific Research - bayesian_model_selection: Bayesian Model Selection - bayesian_multimodeling: Bayesian Multimodeling - bioinformatics: Bioinformatics - computational_geometry: Computational Geometry Algorithms - deep_generative_models: Deep Generative Models - deep_learning: Deep Learning - forecasting_methods: Forecasting Methods - fundamental_ml_theorems: Fundamental Machine Learning Theorems - image_processing_recognition: Image Processing and Recognition - introduction_machine_learning: Introduction to Machine Learning - natural_language_processing: Natural Language Processing - networks_text_analysis: Networks and Text Analysis - neural_architecture_search: Neural Architecture Search - probabilistic_topic_models: Probabilistic Topic Models - recommender_systems: Recommender Systems - rnd_in_ai: Creation of Intelligent Systems - signal_processing: Signal Processing - software_engineering_data_analysis: Software Engineering for Data Analysis - intellectual_data_analysis: Intellectual Data Analysis - optimization_methods: Optimization methods in Machine Learning - + automation_scientific_research: My First Scientific Paper + bayesian_model_selection: Bayesian Model Selection + bayesian_multimodeling: Bayesian Multimodeling + bioinformatics: Bioinformatics + computational_geometry: Computational Geometry + deep_generative_models: Deep Generative Models + deep_learning: Deep Learning + forecasting_methods: Mathematical Forecasting Methods + fundamental_ml_theorems: Fundamental Machine Learning Theorems + image_processing_recognition: Image Processing and Recognition + introduction_machine_learning: Introduction to Machine Learning + natural_language_processing: Natural Language Processing + networks_text_analysis: Networks and Text Analysis + neural_architecture_search: Neural Architecture Search + probabilistic_topic_models: Probabilistic Topic Models + recommender_systems: Recommender Systems + rnd_in_ai: Creation of Intelligent Systems + signal_processing: Signal Processing + software_engineering_data_analysis: Software Engineering for Machine Learning + intellectual_data_analysis: Intellectual Data Analysis + deep_learning_audio: Deep Learning for Audio + programming_practicum_python: Programming Practicum in Python + functional_data_analysis: Functional Data Analysis + computer_vision: Computer Vision + titles: - index: Intelligent Systems Phystech - about: About + index: Intelligent Systems course: Course - people: Lecturers + people: People materials: Materials nir: Research Reports scholarship: Scholarships @@ -176,18 +127,17 @@ titles: paper_guidelines: Papers and theses writing guidelines admission: Admission seminars: Scientific seminars + templates: Templates course: - teachers: Lecturers + teachers: People website: Course Website profile: website: Personal Website - teaches: Teaches + teaches: Courses metatags: - lecturer: Lecturer of the Department of Intelligent Systems at MIPT - bachelor_course: Course of the Bachelor program of Intelligent Systems at MIPT - master_course: Course of the Master program of Intelligent Systems at MIPT - - + lecturer: Lecturer of the Department of Intelligent Systems at MIPT + bachelor_course: Course of the Bachelor program of Intelligent Systems at MIPT + master_course: Course of the Master program of Intelligent Systems at MIPT diff --git a/_i18n/en/_course/automation_scientific_research.md b/_i18n/en/_course/automation_scientific_research.md old mode 100755 new mode 100644 index 87172740..f69f1aa4 --- a/_i18n/en/_course/automation_scientific_research.md +++ b/_i18n/en/_course/automation_scientific_research.md @@ -1,27 +1,28 @@ -### About (My first scientific paper) -This course produces student research papers. It gathers research teams in a society. Each team combines a student, a consultant and an expert. The student is a project driver, who wants to plunge into scientific research activities. The consultant, a graduated student, conducts the research and helps the student. The expert, a professor, states the problem and enlightens the road to the goal. +### About -### Link ko course page -* Course materials: [m1p.org](https://m1p.org/) -* Schedule 2022: [Project m1p_2022](https://github.com/Intelligent-Systems-Phystech/m1p_2022) +This course produces student research papers. It gathers research teams in a society. Each team combines a student, a consultant and an expert. The student is a project driver, who wants to plunge into scientific research activities. The consultant, a graduated student, conducts the research and helps the student. The expert, a professor, states the problem and enlightens the road to the goal. ### Syllabus -* Select your project and tell about it. -* State your problem. -* Plan the experiment. -* Visualise the principle. -* Write the theory. -* Analyse the error. -* Construct your paper. -* Review a paper. -* Select a journal to submit. -* Prepare your presentation. - -### Labworks + +- Select your project and tell about it. +- State your problem. +- Plan the experiment. +- Visualise the principle. +- Write the theory. +- Analyse the error. +- Construct your paper. +- Review a paper. +- Select a journal to submit. +- Prepare your presentation. + +### Labworks + A selected project on applied mathematics or machine learning, conducted by a consultant and professor. The delivery is a paper, a code and a talk. ### Grading + Each week carries several tasks. Each task brings one point exactly according to the schedule of the course. ### Prerequisites + Algebra and analysis at the third year of undergraduate level. diff --git a/_i18n/en/_course/bayesian_model_selection.md b/_i18n/en/_course/bayesian_model_selection.md index 01e5de4c..4518e03a 100755 --- a/_i18n/en/_course/bayesian_model_selection.md +++ b/_i18n/en/_course/bayesian_model_selection.md @@ -1,27 +1,32 @@ ### About + The course is dedicated to the basis of Bayesian Methods in Machine Learning, Bayesian Models’ construction and inference. The notion of optimal bayesian forecast is introduced, and the methods for constructing the one are studied. The methods for handling non-linearities and inhomogeneities in data are discussed. Handling of missing data and optimal model evolution with time are considered from a Bayesian perspective. ### Syllabus -* Introduction: Reminding key definitions from Probability Theory and Statistics. -* Multiple Hypotheses testing and prior election. -* Naive Bayes, its generalizations and optimal bayesian forecast. -* Exponential family of distributions and sufficient statistics. -* Bayesian Linear Regression. Evidence. -* Bayesian Logistics Regression and Feature selection via Max-evidence principle. -* EM-algorithm and Variational EM-algorithm. -* Gaussian process and optimal model evolution with time. -* Constructing adequate multimodels. -* Markov Chain Monte-Carlo (MCMC) methods. -* Hamiltonian Markov Chain Monte-Carlo (HMC) methods. -* Bayesian Optimization. + +- Introduction: Reminding key definitions from Probability Theory and Statistics. +- Multiple Hypotheses testing and prior election. +- Naive Bayes, its generalizations and optimal bayesian forecast. +- Exponential family of distributions and sufficient statistics. +- Bayesian Linear Regression. Evidence. +- Bayesian Logistics Regression and Feature selection via Max-evidence principle. +- EM-algorithm and Variational EM-algorithm. +- Gaussian process and optimal model evolution with time. +- Constructing adequate multimodels. +- Markov Chain Monte-Carlo (MCMC) methods. +- Hamiltonian Markov Chain Monte-Carlo (HMC) methods. +- Bayesian Optimization. ### Labworks + 4 theoretical tasks (performed individually), 1 practical task and 1 competition (performed in teams), 2 tests. Written and oral exam (the latter can be substituted by the presentation on a selected topic). ### Grading + Each theoretical task gives at most 50 / 100 points, while practical one and competition each give up to 50 points. The score for the TOP1 student in each task is doubled (extra points). Written and oral exams add up to 250 together. The final mark is computed by scaling the total score by maximal one assuming no extra points gained. ### Prerequisites -Probability, Basic Machine Learning, Linear Algebra, Optimization. \ No newline at end of file + +Probability, Basic Machine Learning, Linear Algebra, Optimization. diff --git a/_i18n/en/_course/bayesian_multimodeling.md b/_i18n/en/_course/bayesian_multimodeling.md index 69b92db0..40944a43 100755 --- a/_i18n/en/_course/bayesian_multimodeling.md +++ b/_i18n/en/_course/bayesian_multimodeling.md @@ -1,14 +1,19 @@ ### About + The course is devoted to the problem of optimal model selection in machine learning and data analysis tasks. During the course, we investigate the Bayesian approach to model selection, its theoretical and practical aspects. We consider properties of model selection methods both specific to some notable model families or general properties suitable for the most model families. ### Syllabus + The course investigates the properties of model selection for different types of models: from linear to mixtures of experts built on deep learning models. Various approaches to model selection and hyperparameter optimization are discussed, including gradient-based methods, sequential model based optimization methods, methods based on hypernetworks and supernetworks. ### Labworks -4 practical homeworks and 2 oral talks (optional) every term. There is also a simple questionnaire after each pair. + +1 project work and 1 oral talk every term. There is also a simple questionnaire after each pair. ### Grading -The overall score is a sum of scores for practical tasks, talks and the answers for the questionnaire. + +The overall score is a sum of scores for project, talk and the answers for the questionnaire. ### Prerequisites + Statistics, linear algebra, machine learning, deep learning, intro to bayesian inference. diff --git a/_i18n/en/_course/bioinformatics.md b/_i18n/en/_course/bioinformatics.md index 532ef502..c4f9f88b 100755 --- a/_i18n/en/_course/bioinformatics.md +++ b/_i18n/en/_course/bioinformatics.md @@ -1,27 +1,32 @@ ### About + In the course of lectures, unique features of biological data are considered, leading to original statements of recognition and classification problems. It should be noted that for almost all the problems considered in the course, accurate and mathematically sound solutions have not yet been proposed. In this sense, the course represents an extensive field of activity for independent scientific work of students. A system of recognition tasks is formulated that reflects the structure of biological systems and provides a basis for the construction of problem-oriented theories. The fundamentals of the formalism developed to solve the problems of bioinformatics and other poorly formalized problems in the field of advanced biomedical research and sentiment analysis are considered. This formalism is based on the theory of universal and local constraints within the framework of an algebraic approach to recognition. Attention is paid to biomedical applications of the results of intelligent analysis of biological data. ### Syllabus -* From cell biology to recognition tasks. -* iological data, objects and approaches to the formalization of tasks. -* Tasks 1D to 1D: comparison of character sequences. -* 1Ddna tasks. 1Ddna and 3Ddna tasks. Tasks of 1Drna, 2Drna, 3Drna. -* X-ray diffraction analysis and NMR of proteins, 3Db to 3Db and 3Db to 2Db tasks. -* Development of a problem-oriented theory on the example of the problem of recognition of a secondary structure. -* Tasks 1DB to 1Db. -* Tasks 1Db to F and 3D to F and genome annotation task. -* Analysis and synthesis of biological networks. -* Molecular pharmacology and chemoinformatics. -* Biomedical and genetic research. -* Text analysis, use of databases. -* Bio-logic and algorithms. + +- From cell biology to recognition tasks. +- iological data, objects and approaches to the formalization of tasks. +- Tasks 1D to 1D: comparison of character sequences. +- 1Ddna tasks. 1Ddna and 3Ddna tasks. Tasks of 1Drna, 2Drna, 3Drna. +- X-ray diffraction analysis and NMR of proteins, 3Db to 3Db and 3Db to 2Db tasks. +- Development of a problem-oriented theory on the example of the problem of recognition of a secondary structure. +- Tasks 1DB to 1Db. +- Tasks 1Db to F and 3D to F and genome annotation task. +- Analysis and synthesis of biological networks. +- Molecular pharmacology and chemoinformatics. +- Biomedical and genetic research. +- Text analysis, use of databases. +- Bio-logic and algorithms. ### Labworks + Practical tasks will be announced during the lectures. Students can formulate the topics of research tasks themselves. After selecting the task, the work requirements are discussed. ### Grading + Before the start of the oral exam (report-presentation), it is necessary to submit a report on the research work (3-5 pages) carried out on the selected task. ### Prerequisites + Machine learning methods. diff --git a/_i18n/en/_course/computational_geometry.md b/_i18n/en/_course/computational_geometry.md index 14b4e677..03bc662a 100755 --- a/_i18n/en/_course/computational_geometry.md +++ b/_i18n/en/_course/computational_geometry.md @@ -1,19 +1,24 @@ ### About + The course discusses the basic algorithms of computational geometry. ### Syllabus -* Geometric search. -* Construction of convex hulls. -* Defining intersections of objects. -* Voronoi diagrams and Delaunay triangulations. -* Proximity of geometric objects. -* Median axes and skeletons. + +- Geometric search. +- Construction of convex hulls. +- Defining intersections of objects. +- Voronoi diagrams and Delaunay triangulations. +- Proximity of geometric objects. +- Median axes and skeletons. ### Labworks + The course assumes the solution of several laboratory works. ### Grading + The assessment is based on the results of laboratory work and an oral exam. ### Prerequisites + Machine learning, data structures and algorithms. diff --git a/_i18n/en/_course/computer_vision.md b/_i18n/en/_course/computer_vision.md new file mode 100755 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/en/_course/computer_vision.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/en/_course/deep_generative_models.md b/_i18n/en/_course/deep_generative_models.md index f2d8d866..1233b686 100755 --- a/_i18n/en/_course/deep_generative_models.md +++ b/_i18n/en/_course/deep_generative_models.md @@ -1,27 +1,32 @@ ### About + The course is devoted to modern generative models (mostly in the application to computer vision). Special attention is paid to the properties of various classes of generative models, their interrelationships, theoretical prerequisites and methods of quality assessment. The aim of the course is to introduce the student to widely used advanced methods of deep learning. ### Syllabus -1. Generative models overview and motivation. Problem statement. Divergence minimization framework. Autoregressive modelling. -2. Autoregressive models (WaveNet, PixelCNN). Bayesian Framework. Latent Variable Models (LVM). Variational lower bound (ELBO). -3. EM-algorithm, amortized inference. ELBO gradients, reparametrization trick. Variational Autoencoder (VAE). -4. VAE limitations. Posterior collapse and decoder weakening. Tighter ELBO (IWAE). Normalizing flows prerequisities. -5. Normalizing Flow (NF) intuition and definition.. Forward and reverse KL divergence for NF. Linear flows. -6. Autoregressive flows (gausian AR NF/inverse gaussian AR NF). Coupling layer (RealNVP). NF as VAE model. -7. Discrete data vs continuous model. Model discretization (PixelCNN++). Data dequantization: uniform and variational (Flow++). ELBO surgery and optimal VAE prior. Flow-based VAE prior. -8. Flows-based VAE posterior vs flow-based VAE prior. Likelihood-free learning. GAN optimality theorem. -9. Vanishing gradients and mode collapse, KL vs JS divergences. Adversarial Variational Bayes. Wasserstein distance. Wasserstein GAN (WGAN). -10. WGAN with gradient penality (WGAN-GP). Spectral Normalization GAN (SNGAN). f-divergence minimization. Evaluation of implicit models. -11. GAN evaluation (Inception score, FID, Precision-Recall, truncation trick). Discrete VAE latent representations. -12. Vector quantization, straight-through gradient estimation (VQ-VAE). Gumbel-softmax trick (DALL-E). Neural ODE. Adjoint method. -13. Continuous-in-time NF (FFJORD, Hutchinson's trace estimator). Kolmogorov-Fokker-Planck equation and Langevin dynamic. SDE basics. Score matching (Sliced score matching, denoising score matching). -14. Noise conditioned score network (NCSN). Gaussian diffusion process. Denoising diffusion probabilistic model (DDPM). + +1. Generative models overview and motivation. Problem statement. Divergence minimization framework. Autoregressive models (PixelCNN). +2. Normalizing Flow (NF) intuition and definition. Linear NF. Gaussian autoregressive NF. Coupling layer (RealNVP). +3. Forward and reverse KL divergence for NF. Latent variable models (LVM). Variational lower bound (ELBO). EM-algorithm. +4. Amortized inference, ELBO gradients, reparametrization trick. Variational Autoencoder (VAE). NF as VAE model. Discrete VAE latent representations. +5. Vector quantization, straight-through gradient estimation (VQ-VAE). Gumbel-softmax trick (DALL-E). ELBO surgery and optimal VAE prior. Learnable VAE prior. +6. Likelihood-free learning. GAN optimality theorem. Wasserstein distance. +7. Wasserstein GAN (WGAN). f-divergence minimization. GAN evaluation (FID, Precision-Recall, truncation trick). +8. Langevin dynamic. Score matching (Denoising score matching, Noise Conditioned Score Network (NCSN)). Forward gaussian diffusion process. +9. Denoising score matching for diffusion. Reverse Gaussian diffusion process. Gaussian diffusion model as VAE. ELBO for DDPM. +10. Denoising diffusion probabilistic model (DDPM): reparametrization and overview. Denoising diffusion as score-based generative model. Model guidance: classifier guidance, classfier-free guidance. +11. Continuous-in-time NF and neural ODE. Continuity equation for NF log-likelihood. FFJORD and Hutchinson's trace estimator. Adjoint method for continuous-in-time NF. +12. SDE basics. Kolmogorov-Fokker-Planck equation. Probability flow ODE. Reverse SDE. Variance Preserving and Variance Exploding SDEs. +13. Score-based generative models through SDE. Flow matching. Conditional flow matching. Conical gaussian paths. +14. Linear interpolation. Link with diffusion and score matching. Latent space models. ### Labworks + 6 homeworks: theory and practice. ### Grading -Each homework gives 13 points + an exam for 26 points. Final score: (number of points / 8) - 2. + +Each homework gives 15 points + an exam for 30 points. Final score: `min(floor(#points/10), 10)`. ### Prerequisites -Statistics, machine learning, deep learning, intro to bayesian inference. + +Probability theory, statistics, machine learning, basics of deep learning, python, pytorch, intro to bayesian inference. diff --git a/_i18n/en/_course/deep_learning.md b/_i18n/en/_course/deep_learning.md index 615a7541..c47b9c04 100755 --- a/_i18n/en/_course/deep_learning.md +++ b/_i18n/en/_course/deep_learning.md @@ -1,25 +1,34 @@ ### About -An overview course on basic neural network models and their application to image, text, and sound processing tasks. + +This course provides a comprehensive exploration of modern deep learning techniques, from foundational concepts to advanced topics. ### Syllabus -* Feedforward networks. Matrix-vector differentiation. Automatic differentiation. -* Neural network optimization. DropOut. PyTorch. -* Initialization of neural networks. Types of normalization, convolutional neural networks, implementation of convolutional networks in PyTorch. -* Recurrent neural networks. Machine translation task. Attention mechanism. Transformer model. -* Object detection. -* Semantic segmentation. Instance/Panoptic segmentation. -* Reinforcement learning. Markov's decision making process. Bellman equations. -* Policy iteration, Value iteration algorithms. Q-learning. DQN model. -* Algorithm Reinforce, A2C algorithm. Multi-armed bandits. -* Generative models. Variational autoencoder model. -* Autoregressive models: PixelCNN, PixelRNN. Reparametrization trick. -* Generative adversarial networks and their modifications. Image quality metrics. + +1. MLP, Backpropagation +2. Optimization, Regularization +3. Initialization, Normalization, CNN +4. Introduction to Natural Language Processing, Word Embeddings +5. RNN, LSTM, Attention, Transformer +6. Classification, Object Detection +7. Segmentation +8. Multi-armed Bandits, Bellman Equations, Monte Carlo Methods, TD Learning, Q-Learning +9. Planning and Double Learning, Policy Improvement, Policy Gradient +10. Autoregression, VAE, GAN +11. Diffusion, Flow Matching +12. LLMs, Fine-tuning, LoRA, RAG, Agents +13. Multi-modal Models, CLIP, Qwen-VL +14. Quantization, Pruning, Distillation, KV-Cache, Flash Attention ### Labworks -5 practical tasks and 1 lab work. Each task is evaluated from 10 points. The exam is evaluated from 10 points. + +6 homeworks on practical implementation of Deep Learning models. ### Grading -0.7 * semester points + 0.3 * exam points. + +6 homeworks give 70 points in total + an exam for 30 points. Final score: `min(round(#points/10), 10)`. ### Prerequisites -Machine learning, statistics, optimization methods. + +- Probability Theory + Statistics +- Machine Learning +- Python diff --git a/_i18n/en/_course/deep_learning_audio.md b/_i18n/en/_course/deep_learning_audio.md new file mode 100755 index 00000000..d0d7c4ee --- /dev/null +++ b/_i18n/en/_course/deep_learning_audio.md @@ -0,0 +1,40 @@ +### About + +The course is devoted to modern deep learning approaches for audio processing and analysis. Special attention is paid to digital signal processing fundamentals, automatic speech recognition systems, text-to-speech synthesis, and neural audio generation methods. The aim of the course is to introduce students to advanced techniques in audio machine learning and their practical applications. + +### Syllabus + +1. **Digital Signal Processing**: Audio fundamentals, spectrograms, STFT, and classical audio preprocessing techniques. +2. **Automatic Speech Recognition I**: Word Error Rate (WER), Connectionist Temporal Classification (CTC), Listen-Attend-Spell (LAS), and beam search algorithms. +3. **Automatic Speech Recognition II**: RNN-Transducer (RNN-T), Conformer architecture, Whisper model, language models in ASR, and Byte-Pair Encoding (BPE). +4. **Key-word Spotting (KWS)**: Wake word detection, small-footprint models, and streaming KWS systems. +5. **Text-to-Speech I**: Tacotron architecture, FastSpeech models, and guided attention mechanisms. +6. **Text-to-Speech II**: Neural vocoders including WaveNet, Parallel WaveGAN, and DiffWave for high-quality audio synthesis. +7. **Voice Conversion**: Voice transformation techniques and neural approaches to voice cloning. +8. **Self-supervised Learning in Audio**: Wav2Vec, HuBERT, and other self-supervised approaches for audio representation learning. +9. **Unsupervised Learning in Audio**: Clustering, representation learning, and unsupervised audio analysis methods. +10. **Music Generation with Neural Networks**: AI-powered music composition and generation techniques. + +### Lectures and Seminars + +The course includes both theoretical lectures and practical seminars with hands-on coding exercises. Topics covered: + +- **Lectures**: Fundamental concepts, model architectures, and theoretical foundations +- **Seminars**: Practical implementation using PyTorch, audio preprocessing, model training, and evaluation + +### Labworks + +4 homeworks covering practical aspects of audio deep learning: + +1. **Audio Classification & Preprocessing**: Fundamental audio processing and classification tasks +2. **ASR with CTC**: Implementing connectionist temporal classification for speech recognition +3. **ASR with RNN-T**: Advanced speech recognition using RNN-Transducer architecture +4. **Text-to-Speech**: Building FastPitch-based text-to-speech systems + +### Grading + +Each homework gives 2 points + final test for 2 points. Maximum score: 4×2 + 2 = **10 points**. + +### Prerequisites + +Digital signal processing basics, machine learning fundamentals, deep learning with PyTorch, and basic understanding of sequence modeling. diff --git a/_i18n/en/_course/forecasting_methods.md b/_i18n/en/_course/forecasting_methods.md index 4491d8ab..894b7db4 100755 --- a/_i18n/en/_course/forecasting_methods.md +++ b/_i18n/en/_course/forecasting_methods.md @@ -1,25 +1,27 @@ ### About -The course joins two parts of the problem statements in Machine Learning. The first part comes from the structure of the measured data. The data come from Physics, Chemistry and Biology and have intrinsic algebraic structure. This structure is part of the theory that stands behind the measurement. The second part comes from errors of the measurement. The stochastic nature errors request the statistical methods of analysis. So this course joins algebra and statistics. It is devoted to the problem of predictive model selection. + +The course joins two parts of the problem statements in Machine Learning. The first part comes from the structure of the measured data. The data come from Physics, Chemistry and Biology and have intrinsic algebraic structure. This structure is part of the theory that stands behind the measurement. The second part comes from errors of the measurement. The stochastic nature errors request the statistical methods of analysis. So this course joins algebra and statistics. It is devoted to the problem of predictive model selection. ### Syllabus -* Autoregressive models. -* Correlation and Convergence Analysis. -* Tensor decompositions. -* Neural differential equations. -* Continuous time and streams. -* Metric methods and tensors. -* Spectral methods. -* Spectral graph models. -* Geometric data analysis. - -### Labworks -Two personal labworks on brain data analysis include the problem statement and the computational experiment. The delivery is a two-page report with the problem and experimental results, a code and a talk. + +- Autoregressive models. +- Correlation and Convergence Analysis. +- Tensor decompositions. +- Neural differential equations. +- Continuous time and streams. +- Metric methods and tensors. +- Spectral methods. +- Spectral graph models. +- Geometric data analysis. + +### Labworks + +Two personal labworks on brain data analysis include the problem statement and the computational experiment. The delivery is a two-page report with the problem and experimental results, a code and a talk. ### Grading -Questionnaires during lectures (3), two labworks (2+2), the final exam: topics and problems with discussion (3). + +Questionnaires during lectures (3), two labworks (2+2), the final exam: topics and problems with discussion (3). ### Prerequisites -Algebra, analysis and physics at the graduate level. -### Course page -[with detailed schedule and materials](https://m1p.org/mf) +Algebra, analysis and physics at the graduate level. diff --git a/_i18n/en/_course/functional_data_analysis.md b/_i18n/en/_course/functional_data_analysis.md new file mode 100755 index 00000000..15a6fd62 --- /dev/null +++ b/_i18n/en/_course/functional_data_analysis.md @@ -0,0 +1,131 @@ +**Channels** + +- [The 2025 course seminar](https://t.me/+XyXmEXRlrXB9dZKD) +- [The chat-link FDA group](https://t.me/+XyXmEXRlrXB9dZKD) + +**When** + +- September 4, 11, 18, 25 — **Thursdays** at 10:30 · [m1p.org/go_zoom](https://m1p.org/go_zoom) +- October (most likely) — **Saturdays** at 10:30 + +--- + +## Foundation models for spatial-time series + +Foundation AI models are universal models for a wide set of problems. This project investigates their theoretical properties on **spatial-time series**—data used across sciences to generalize knowledge and make forecasts. Core user-level tasks: _forecasting_ and _generation_ of time series; _analysis_ and _classification_; _change-point detection_; _causal inference_. These models are trained on massive datasets. Our goal is to compare architectures to find an optimal one that solves the above for a broad range of spatial time series. + +## Functional data analysis + +We assume continuous time and study state-space changes $\frac{d\mathbf{x}}{dt}$ via neural ODEs/SDEs. We analyze multivariate/multidimensional series with tensor representations; model strong cross-correlations in **Riemannian** spaces. Many medical series are periodic; the base model is the pendulum $\frac{d^2 x}{dt^2} = -c\sin x$. We use physics-informed neural networks (PINNs). Practical experiments involve multiple sources; we use canonical correlation analysis with a **latent state space** to align source/target manifolds and enable generation in both. + +## Applications + +Any field with continuous time/space data from multimodal sources: climate, neural interfaces, solid-state physics, electronics, fluid dynamics, and more. We collect both theory and practice. + +--- + +## Fall 2025: Foundation models for time series + +### Topics to discuss + +1. State Space Models, Convolution, SSA, SSM (Spectral Submanifolds) +2. Neural & Controlled ODE, Neural PDE, Geometric Learning +3. Operator Learning, Physics-informed learning, multimodeling +4. Spatio-Temporal Graph Modeling: graph convolution & metric tensors +5. Riemannian models; time series generation +6. AI for science: mathematical modeling principles + +Outside the course: data-driven tensor analysis, differential forms, spinors. + +### State of the Art in 2025 + +In December 2024, a NeurIPS workshop “Foundational models for science” reflected this theme: + +1. Foundation Models for Science: Progress, Opportunities, and Challenges — [URL](https://neurips.cc/virtual/2024/workshop/84714) +2. Foundation Models for the Earth system — [UPL, no paper](https://neurips.cc/virtual/2024/107817) +3. Foundation Methods for foundation models for scientific machine learning — [URL, no paper](https://neurips.cc/virtual/2024/107819) +4. AI-Augmented Climate simulators and emulators — [URL, no paper](https://neurips.cc/virtual/2024/107822) +5. Provable in-context learning of linear systems and linear elliptic PDEs with transformers — [NIPS](https://openreview.net/forum?id=xDstmuxn1D) +6. VSMNO: Solving PDE by Utilizing Spectral Patterns of Different Neural Operators — [NIPS PDF](https://openreview.net/pdf?id=oCT8pYix5e) + +### March 2025 Physics Problem Simulations + +- The Well: a Large-Scale Collection of Diverse Physics Simulations for ML — [arXiv](https://arxiv.org/pdf/2412.00568) · [Code](https://polymathic-ai.org/the_well/data_format/) +- Polymathic: Advancing Science through Multi-Disciplinary AI — [blog](https://polymathic-ai.org/) +- Long Term Memory: The Foundation of AI Self-Evolution — [arXiv](https://arxiv.org/html/2410.15665v1) +- Distilling Free-Form Natural Laws from Experimental Data (2009) — [Science](https://www.science.org/doi/abs/10.1126/science.1165893) · [comment](https://arxiv.org/pdf/1210.7273) · [medium](https://medium.com/@lotussavy/distilling-free-form-natural-laws-from-experimental-data-f55341ae0fa6) +- Deep learning for universal linear embeddings of nonlinear dynamics — [Nature](https://www.nature.com/articles/s41467-018-07210-0) +- A comparison of data-driven approaches to low-dimensional ocean models (2021) — [arXiv](https://arxiv.org/abs/2108.00818) +- Applications of DL to Ocean Data Inference & Subgrid Parameterization (2018) — [preprint](https://eartharxiv.org/repository/view/1142/) +- On energy-aware hybrid models (2024) — [doi](https://doi.org/10.1029/2024MS004306) + +### Spatial-Temporal Graph Modeling + +- Graph WaveNet — [arXiv](https://arxiv.org/abs/1906.00121) +- Diffusion Convolutional Recurrent Neural Network (DCRNN) — [ICLR](https://arxiv.org/abs/1707.01926) +- Time-SSM: Simplifying & Unifying State Space Models — [arXiv](https://arxiv.org/pdf/2405.16312) +- State Space Reconstruction for Multivariate Time Series — [arXiv](https://arxiv.org/abs/0809.2220) +- Longitudinal predictive modeling of tau progression — [NeuroImage 2021](https://www.sciencedirect.com/science/article/pii/S1053811921004031?via%3Dihub) + +--- + +## Work arrangements + +| **Week** | **Date** | **Theme** | **Delivery** | +| -------: | :------- | :------------------------------------------------------------------------------------------------------------------------------------ | :---------------------- | +| 1 | Sep 4 | Preliminary discussion — [pdf](https://github.com/vadim-vic/Foundation-ts/tree/main/doc/Foundation_models_for_time_series_Week_1.pdf) | | +| 2 | Sep 11 | Problem statement — [pdf](https://github.com/vadim-vic/Foundation-ts/tree/main/doc/Foundation_models_for_time_series_Week_2.pdf) | | +| 3 | Sep 18 | Preliminary solution | Group talk & discussion | +| 4 | Sep 25 | Minimum deployment | Group report | +| 5 | Oct 4+ | FDA | Personal talks | +| 13 | Nov 29 | Final discussion | Group talks | + +--- + +## Structure of seminars + +The semester lasts **12 weeks**; six alternate weeks are for homework. + +- **Odd week:** topic intro + homework theme handout. +- **Every week:** essay discussion; collect improvement list. +- **Odd week:** discuss improved essays; integrate into a joint structure. + +### Scoring + +Group activity: cross-ranking with **Kemeny median**. Personal talks contribute to score. + +--- + +## Week 3 — Homework 1 + +1. Form a group. +2. Discuss goals and a solution (\[see the problem statement]). +3. Review solution approaches. +4. Select an LLM-GPT. +5. Run the code; verify it works. + + - Store code in the group repository. + - Store slides/report as well. + +6. Make a 10-minute talk covering: + + - Functionality and architecture of the model. + - Why you selected this model. + - Alternative models considered. + +### Requirements for the text & discussion + +1. Comprehensive explanation of the discussed method/question. +2. Principles only; **no experiments**. +3. \~Two pages. +4. Target reader: 2nd–3rd-year student. +5. One figure is **mandatory**. +6. Brief reference to DL structure is welcome. +7. Talk may be a slide or the text itself. +8. References with DOIs. +9. State how it was generated. +10. Note observed gaps to revisit later. + +### Style remarks for the essays + +Automatic text generation raises the bar for clarity and authorship. Use generative tools to **train persuasion skills**; write for a **thesis defense committee**. diff --git a/_i18n/en/_course/fundamental_ml_theorems.md b/_i18n/en/_course/fundamental_ml_theorems.md index 02636a5d..b3adef70 100644 --- a/_i18n/en/_course/fundamental_ml_theorems.md +++ b/_i18n/en/_course/fundamental_ml_theorems.md @@ -1,28 +1,33 @@ ### About + The goal of the course is to learn how to rigorously formulate machine learning problems and to show the role of the mathematical approach. The skills acquired in this course are the basis for writing Bachelor's, Master's and Ph.D works in machine learning and applied mathematics. The course includes discussions of axiomatic systems, theorems and their proofs that are relevant in machine learning. Their influence on practical applications is discussed. ### Syllabus -* Gauss-Markov theorem -* Singular Value Decomposition theorem -* Principal Component Analysis and Karhunen-Loeve Decomposition -* Karush-Kuhn-Tucker theorem and optimization -* Kolmogorov and Arnold theorems, Tsybenko universal approximator theorem, deep neural network theorem -* The free lunch theorem in machine learning, Wolpert -* Metric spaces: RKHS Aronzhine, Mercer's theorem -* Scheme theorem, Holland -* Convolution theorem, Parseval's theorem -* PAC-learning, compression implies learning -* Representation theorem -* Theorems about boosting, bootstrap -* Variational approximation -* Takens' embedding theorem -* Green, Stokes, deRham theorems in geometric learning + +- Gauss-Markov theorem +- Singular Value Decomposition theorem +- Principal Component Analysis and Karhunen-Loeve Decomposition +- Karush-Kuhn-Tucker theorem and optimization +- Kolmogorov and Arnold theorems, Tsybenko universal approximator theorem, deep neural network theorem +- The free lunch theorem in machine learning, Wolpert +- Metric spaces: RKHS Aronzhine, Mercer's theorem +- Scheme theorem, Holland +- Convolution theorem, Parseval's theorem +- PAC-learning, compression implies learning +- Representation theorem +- Theorems about boosting, bootstrap +- Variational approximation +- Takens' embedding theorem +- Green, Stokes, deRham theorems in geometric learning ### Labworks + Presentation of the formulations, proofs and methods of application, significance, of theorems. ### Grading + The quality of presentations and the quality of questions to the speaker from each student. ### Prerequisites + Algebra and analysis of the third year of MIPT. diff --git a/_i18n/en/_course/image_processing_recognition.md b/_i18n/en/_course/image_processing_recognition.md index 7f03af03..9c802761 100755 --- a/_i18n/en/_course/image_processing_recognition.md +++ b/_i18n/en/_course/image_processing_recognition.md @@ -1,26 +1,31 @@ ### About + The course is based on mathematical methods of pattern recognition used for the analysis and classification of images in computer vision systems. Image transformations are considered in order to generate feature descriptions. The methods of point, spatial geometric, algebraic and inter-frame image processing are studied. Methods of feature generation based on the decomposition of images by basic functions, statistical analysis of image texture, as well as image shape analysis are considered. Methods of construction of metrics for image comparison (comparison of spectral decompositions, overlay and alignment of images) are considered. And also questions of application of the studied methods in applied problems of computer vision. The tasks of text recognition in document images, the tasks of biometric identification of an individual by the texture of the iris, by the shape of the palm, fingerprint, face profile are considered. ### Syllabus -* Subject and tasks of digital image processing and recognition. -* Spatial image processing methods. -* Geometric and algebraic methods of image processing. -* Methods of inter-frame image processing. -* Image analysis based on decomposition by basic functions. -* Statistical methods of texture analysis. -* Methods of image shape analysis. -* Metrics for measuring image similarity. -* Text recognition based on document images. -* Biometric identification based on image recognition. -* Dynamic scene recognition. + +- Subject and tasks of digital image processing and recognition. +- Spatial image processing methods. +- Geometric and algebraic methods of image processing. +- Methods of inter-frame image processing. +- Image analysis based on decomposition by basic functions. +- Statistical methods of texture analysis. +- Methods of image shape analysis. +- Metrics for measuring image similarity. +- Text recognition based on document images. +- Biometric identification based on image recognition. +- Dynamic scene recognition. ### Labworks + Homeworks on image processing and classification. ### Grading + The assessment is based on the results of laboratory work and an oral exam. ### Prerequisites + Machine learning, linear algebra. diff --git a/_i18n/en/_course/intellectual_data_analysis.md b/_i18n/en/_course/intellectual_data_analysis.md index 2e5ee5d1..29b6310d 100755 --- a/_i18n/en/_course/intellectual_data_analysis.md +++ b/_i18n/en/_course/intellectual_data_analysis.md @@ -1,10 +1,9 @@ ### About + The course introduces students to the full cycle of creating machine learning models for research purposes. The main stages of the semester: analysis of an applied problem and formulation of the problem, building a model, performing a computational experiment, error analysis. The result of the work of a group of students is a library of models for a fixed applied problem or class of problems. -[Course page](https://github.com/intsystems/ida) - - ### Grading + Evaluated: the student’s qualifications and his personal contribution to the project. diff --git a/_i18n/en/_course/introduction_machine_learning.md b/_i18n/en/_course/introduction_machine_learning.md index f6f200f5..15f49664 100755 --- a/_i18n/en/_course/introduction_machine_learning.md +++ b/_i18n/en/_course/introduction_machine_learning.md @@ -1,34 +1,39 @@ ### About + The course covers the main tasks of teaching by use cases: classification, clustering, regression, dimension reduction. The methods of their solution, both classical and new, created over the past 10-15 years, are being studied. The emphasis is on a deep understanding of the mathematical foundations, relationships, advantages and limitations of the methods under consideration. Theorems are mostly given without proofs. ### Syllabus -* Linear classifier and stochastic gradient. -* Metric methods of classification and regression. -* Support vector machine. -* Linear regression. Nonlinear regression. -* Model selection criteria and feature selection methods. -* Logical classification methods. -* Linear ensembles. Advanced methods of ensembling. -* Density estimation and Bayesian classification. -* Clustering and partial learning. -* Deep neural networks. -* Deep neural networks for unsupervised learning. -* Vector representations of texts and graphs. -* Attention models and transformers. -* Topic modeling. -* Learning to rank. -* Recommendation systems. -* Search for associative rules. -* Adaptive forecasting methods. -* Incremental and online learning. -* Reinforcement learning. -* Active learning. + +- Linear classifier and stochastic gradient. +- Metric methods of classification and regression. +- Support vector machine. +- Linear regression. Nonlinear regression. +- Model selection criteria and feature selection methods. +- Logical classification methods. +- Linear ensembles. Advanced methods of ensembling. +- Density estimation and Bayesian classification. +- Clustering and partial learning. +- Deep neural networks. +- Deep neural networks for unsupervised learning. +- Vector representations of texts and graphs. +- Attention models and transformers. +- Topic modeling. +- Learning to rank. +- Recommendation systems. +- Search for associative rules. +- Adaptive forecasting methods. +- Incremental and online learning. +- Reinforcement learning. +- Active learning. ### Labworks + No. ### Grading + At the end of the course, students take an oral exam on all topics of the course. ### Prerequisites + Probability theory, statistics, optimization methods, linear algebra. diff --git a/_i18n/en/_course/natural_language_processing.md b/_i18n/en/_course/natural_language_processing.md index 7b9292ca..9ede6f3b 100755 --- a/_i18n/en/_course/natural_language_processing.md +++ b/_i18n/en/_course/natural_language_processing.md @@ -1,27 +1,32 @@ ### About + The course covers the main tasks and mathematical methods of natural language processing. ### Syllabus -* Preprocessing, feature extraction and classification. -* Vector representations of words. -* The task of marking sequences (tagging). The Linear-CRF model. -* Recurrent neural network models: GRNN, LSTM. -* Machine translation. The Sequence-to-sequence approach. The mechanism of attention. -* Transformer architecture. -* The task of language modeling. -* Statistical and neural network language models. -* The task of generating a natural language. -* Contextual vector representations of words. -* Transfer learning to NLP. -* The BERT model and its modifications. -* Text classification. -* Topic modeling and its applications. + +- Preprocessing, feature extraction and classification. +- Vector representations of words. +- The task of marking sequences (tagging). The Linear-CRF model. +- Recurrent neural network models: GRNN, LSTM. +- Machine translation. The Sequence-to-sequence approach. The mechanism of attention. +- Transformer architecture. +- The task of language modeling. +- Statistical and neural network language models. +- The task of generating a natural language. +- Contextual vector representations of words. +- Transfer learning to NLP. +- The BERT model and its modifications. +- Text classification. +- Topic modeling and its applications. ### Labworks + The course includes four practical tasks and an exam. The deadline for completing each task is 2 weeks. You can get up to 10 points for each task. For each day of delay, a penalty of 1 point is assigned. ### Grading -0.7 * hw points / 5 + 0.3 * exam points. + +0.7 _ hw points / 5 + 0.3 _ exam points. ### Prerequisites + Machine learning, deep learning, Python. diff --git a/_i18n/en/_course/networks_text_analysis.md b/_i18n/en/_course/networks_text_analysis.md index f7df25fd..7f790347 100755 --- a/_i18n/en/_course/networks_text_analysis.md +++ b/_i18n/en/_course/networks_text_analysis.md @@ -1,27 +1,32 @@ ### About + The methods and technologies used in data mining and based on the concepts of similarity, proximity, analogy are considered. The idea of similarity is inherent in human thinking, it has given rise to a whole range of approaches for all fundamental tasks of IAD, among which the main focus of the course is on classification, regression recovery, clustering, recovery of missing data. The theoretical basis for the construction, implementation and analysis of a wide range of models and methods of IAD is presented. Methods of constructing and calculating similarity functions, matching similarities on various sets of objects, synthesis of new ways of comparing objects based on existing ones are considered. A complex of technologies designed for efficient representation and processing of metric information by computing systems is considered. Heuristic data models describing the initial information about recognition objects based on various implementations of the concept of similarity are investigated. The problems requiring solutions in the implementation of these models are considered. Special data structures and algorithms are being studied to effectively configure and use the studied models. ### Syllabus -* The main approaches to the task of similarity. -* Classical definition of metric and metric space. -* Local metrics and their extension to the entire space. -* Geometric subsets of general metric spaces. -* Examples of metric spaces. -* Classification of similarity functions. -* Characteristics of metrics. -* Metric transformations. -* Implementation of metrics. -* The principle of self-organization. -* Metrics on finite sets. -* Decomposition of MC by finite systems of MC. + +- The main approaches to the task of similarity. +- Classical definition of metric and metric space. +- Local metrics and their extension to the entire space. +- Geometric subsets of general metric spaces. +- Examples of metric spaces. +- Classification of similarity functions. +- Characteristics of metrics. +- Metric transformations. +- Implementation of metrics. +- The principle of self-organization. +- Metrics on finite sets. +- Decomposition of MC by finite systems of MC. ### Labworks + No. ### Grading + Exam based on course materials. ### Prerequisites + Machine learning, algorithms and data structures. diff --git a/_i18n/en/_course/neural_architecture_search.md b/_i18n/en/_course/neural_architecture_search.md index 5f7036a6..6c099f8f 100755 --- a/_i18n/en/_course/neural_architecture_search.md +++ b/_i18n/en/_course/neural_architecture_search.md @@ -1,25 +1,30 @@ ### About + The course is devoted to modern methods of constructing complex neural network architectures and choosing optimal structures. ### Syllabus -* Overview of neural network types and architecture descriptions. -* Genetic algorithms from GMDH to WANN. -* Quality criteria for selecting structures (to be discussed in a couple of weeks). -* A priori assumptions about the model structure, structural parameters distribution. -* Methods for optimization of structural parameters. -* Online training and multi-armed bandits to architecture search. -* Reinforcement learning for architecture search. -* Knowledge transfer between neural networks and optimization of structural parameters. -* Random processes for architecture search. -* Generative adversarial networks and the architecture search. -* Generation and rejection of structures. -* Two-level Bayesian selection and Metropolis-Hastings sampling. + +- Overview of neural network types and architecture descriptions. +- Genetic algorithms from GMDH to WANN. +- Quality criteria for selecting structures (to be discussed in a couple of weeks). +- A priori assumptions about the model structure, structural parameters distribution. +- Methods for optimization of structural parameters. +- Online training and multi-armed bandits to architecture search. +- Reinforcement learning for architecture search. +- Knowledge transfer between neural networks and optimization of structural parameters. +- Random processes for architecture search. +- Generative adversarial networks and the architecture search. +- Generation and rejection of structures. +- Two-level Bayesian selection and Metropolis-Hastings sampling. ### Самостоятельная работа + The laboratory work consists in the study of the architecture search method. The first job is to analyze a ready-made method, the second job is to propose and program your own method. The work report is a page of text with a formal description of the method with sufficient detail for code recovery and error analysis (basic criteria complexity, stability, accuracy). The interface to the class is fixed and common to everyone, as are the selections. There is a general table with the results, and a private error analysis of each method. ### Оценивание + A total of 10 points, two points for answering questions during lectures, four points each for two laboratory work. It is not the accuracy of the approximation that is evaluated, but the quality of the code and error analysis. ### Требуемые знания + Machine learning, deep learning, Bayesian model selection. diff --git a/_i18n/en/_course/optimization_methods.md b/_i18n/en/_course/optimization_methods.md deleted file mode 100755 index b00becf0..00000000 --- a/_i18n/en/_course/optimization_methods.md +++ /dev/null @@ -1,10 +0,0 @@ -### About - -### Syllabus - -### Labworks - -### Grading - -### Prerequisites - diff --git a/_i18n/en/_course/probabilistic_topic_models.md b/_i18n/en/_course/probabilistic_topic_models.md index 428df7de..5fb5d863 100755 --- a/_i18n/en/_course/probabilistic_topic_models.md +++ b/_i18n/en/_course/probabilistic_topic_models.md @@ -1,25 +1,30 @@ ### About + The special course studies probabilistic topic modeling of collections of text documents. The topic model determines which topics are contained in a large text collection, and which topics each document belongs to. Topic models allow you to search for texts by meaning, not by keywords, and create a new generation of information search engines based on the paradigm of semantic exploratory search (exploratory search). Topic models for classification, categorization, segmentation, summarization of natural language texts, as well as for recommendation systems, analysis of bank transactional data, analysis of biomedical signals are considered. The special course develops a multi-criteria approach to the construction of models with specified properties - additive regularization of topic models (ARTM). It is based on the regularization of incorrectly set stochastic matrix decomposition problems. Particular attention is paid to the methods of linguistic regularization for modeling the coherence of the text. Students are supposed to conduct numerical experiments on model and real data using the BigARTM topic modeling library. ### Syllabus -* The task of topic modeling. -* Online EM algorithm and regularizers. -* Exploratory information search. -* Assessment of the quality of topic models. -* BigARTM and basic tools. -* EM algorithm theory. -* Bayesian training of the LDA model. -* Topic models of word compatibility. -* Dependency analysis. -* Multimodal topic models. -* Modeling the local context. -* Summarization and visualization. + +- The task of topic modeling. +- Online EM algorithm and regularizers. +- Exploratory information search. +- Assessment of the quality of topic models. +- BigARTM and basic tools. +- EM algorithm theory. +- Bayesian training of the LDA model. +- Topic models of word compatibility. +- Dependency analysis. +- Multimodal topic models. +- Modeling the local context. +- Summarization and visualization. ### Labworks + No. ### Grading + The condition for passing the course is the performance of individual practical tasks. ### Prerequisites + Linear algebra, mathematical analysis, probability theory. diff --git a/_i18n/en/_course/programming_practicum_python.md b/_i18n/en/_course/programming_practicum_python.md new file mode 100755 index 00000000..45642d92 --- /dev/null +++ b/_i18n/en/_course/programming_practicum_python.md @@ -0,0 +1,56 @@ +### About + +The course is devoted to practical programming skills in Python with emphasis on data science and machine learning applications. Special attention is paid to Python fundamentals, data analysis tools, neural networks, and industrial development practices. The aim of the course is to provide students with comprehensive Python programming skills essential for modern data science and ML engineering. + +### Syllabus + +The course is structured into three logical blocks covering progression from basic Python to industrial applications: + +#### Block 1: Introduction to Python Language + +1. **Python Introduction**: Built-in data types, memory model, and language fundamentals +2. **Functions and Iterators**: Function definition, iterators, generators, and advanced Python constructs +3. **Object-Oriented Programming I**: Language features, attributes, inheritance, and class design principles + +#### Block 2: Python for Machine Learning + +4. **Data Analysis Tools**: NumPy, Pandas, Matplotlib, and essential data manipulation libraries +5. **Machine Learning Tools**: Scikit-learn, model training, evaluation, and ML pipeline development +6. **Object-Oriented Programming II**: Typing, polymorphism, data classes, decorators, and advanced OOP concepts +7. **Neural Networks**: Deep learning frameworks, PyTorch/TensorFlow, and neural network implementation + +#### Block 3: Industrial Development Elements + +8. **Virtual Environments and Containers**: Environment management, Docker, and deployment considerations +9. **Python Modules and Web Clients**: Module system, HTTP clients, and API interaction +10. **Server-Side Web Development**: Flask/FastAPI, REST APIs, and web service architecture +11. **Code Efficiency Methods**: Performance optimization, profiling, and best practices for production code + +### Lectures and Practical Assignments + +The course combines theoretical lectures with hands-on practical assignments: + +- **Format**: Interactive lectures + coding assignments +- **Structure**: 11 lectures covering theoretical foundations and practical implementations +- **Assignments**: 4 comprehensive practical tasks building upon each other + +### Labworks + +4 practical assignments covering the complete Python development workflow: + +1. **Introduction to Python**: Basic language constructs, data structures, and programming fundamentals +2. **Data Analysis and Machine Learning**: Data manipulation, statistical analysis, and ML model implementation +3. **Neural Networks**: Deep learning model development, training, and evaluation +4. **Web Server for ML Models**: Full-stack ML application with training and inference capabilities + +### Grading + +To pass the course and receive credit, students must: + +- **Total Score**: Accumulate at least 60 points across all 4 assignments +- **Minimum per Assignment**: Score at least 10 points on each individual assignment +- **Maximum Score**: 100 points total (25 points per assignment) + +### Prerequisites + +Basic programming knowledge, mathematical foundations (linear algebra, statistics), and familiarity with algorithmic thinking. diff --git a/_i18n/en/_course/recommender_systems.md b/_i18n/en/_course/recommender_systems.md index 598bbdbd..16cf00ca 100644 --- a/_i18n/en/_course/recommender_systems.md +++ b/_i18n/en/_course/recommender_systems.md @@ -1,11 +1,13 @@ ### About + Course objective is to provide comprehensive introduction to the field of Recommender Systems. - first part of the course will cover theoratical background for RecSys -- next, we will discuss practical aspects of recommender system training and evaluation +- next, we will discuss practical aspects of recommender system training and evaluation - finally we will briefly cover counterfactual evaluation from logged feedback ### Syllabus + 1. Introduction 2. Neighborhood-Based models 3. Matrix Factorization models @@ -16,10 +18,13 @@ Course objective is to provide comprehensive introduction to the field of Recomm 8. Counterfactual evaluation ### Labworks + Two homeworks during the course ### Grading + Based on homework results ### Prerequisites + Machine learning, deep learning diff --git a/_i18n/en/_course/rnd_in_ai.md b/_i18n/en/_course/rnd_in_ai.md index fbed6c5c..d7d032c3 100644 --- a/_i18n/en/_course/rnd_in_ai.md +++ b/_i18n/en/_course/rnd_in_ai.md @@ -1,42 +1,49 @@ ### About + This is the extension of “Automation of Scientific Research” course. The work is organized in teams (2-3 people). Students will prepare weekly presentation of the team's work: 5 minutes presentation + 5 minutes discussion with other students. **Criteria for the project**: + 1. The entire project must be on GitHub under an OpenSource license (MIT) 2. The project must contain the code and instructions for launching it. - 1. The basic code in jupyter notebook to demonstrate the concept of work and plotting from the article should be run with colab. + 1. The basic code in jupyter notebook to demonstrate the concept of work and plotting from the article should be run with colab. 2. The source code of the computational experiment should be run on a Unix system by executing two commands (possibly in a special docker image): - * python3 train.py - for training models. - * python3 test.py - for testing, obtaining the results of the experiment. + - python3 train.py - for training models. + - python3 test.py - for testing, obtaining the results of the experiment. 3. The documentation for the code is sphinx. 3. The project should contain the manuscript of the article using a stylistic from arXiv - for unification. 4. If the project implies non-synthetic data, then there should be an instruction for obtaining this data, as well as a script for obtaining them. If the data is specific, then they need to be posted on one of the file storages. ### Syllabus -* Introductory lecture. -* Projects discussion. -* Project structure. -* The first checkpoint. -* Paper structure. -* How to build a jupiter notebook correctly. -* The second checkpoint. -* The correct code is not in jupiter notebook! -* Data storage for an experiment. -* The third checkpoint. -* Code documentation using sphinx. -* Docker for the experiment code. -* The fourth checkpoint. -* Evaluation. + +- Introductory lecture. +- Projects discussion. +- Project structure. +- The first checkpoint. +- Paper structure. +- How to build a jupiter notebook correctly. +- The second checkpoint. +- The correct code is not in jupiter notebook! +- Data storage for an experiment. +- The third checkpoint. +- Code documentation using sphinx. +- Docker for the experiment code. +- The fourth checkpoint. +- Evaluation. ### Labworks + Writing scientific paper. ### Grading + There are 4 checkpoints in the course, 3 points are given for each -1. Research of the subject area - analysis of the problem. + +1. Research of the subject area - analysis of the problem. 2. Theoretical results. 3. Computational experiment. 4. Github project. ### Prerequisites -Machine learning, deep learning, Python. \ No newline at end of file + +Machine learning, deep learning, Python. diff --git a/_i18n/en/_course/signal_processing.md b/_i18n/en/_course/signal_processing.md index ba2121ea..4d9e51a1 100755 --- a/_i18n/en/_course/signal_processing.md +++ b/_i18n/en/_course/signal_processing.md @@ -1,22 +1,27 @@ ### About + The course is devoted to the use of methods of mathematical modelling and theoretical physics in signal processing. It applies methods for machine learning model selection to various types of signals: image, video and sound. It discusses techniques to construct systems of heterogenous signal models. ### Syllabus -* Multi-view, kernels and metric spaces, RKHS for brain Imaging. -* Spherical harmonics for mechanical motion modelling. -* Riemannian geometry on Shapes and diffeomorphisms for fMRI. -* Manifolds, Levi-Chivita connection and curvature tensors. -* Differential forms and fibre bundles with examples. -* Navier-Stokes equations and viscous flow. -* Geometric algebra, exterior product and quaternions. -* Graph convolution and continuous Laplace operators, diffusion models. -* Homology and cohomology, differential forms for model ensembling. + +- Multi-view, kernels and metric spaces, RKHS for brain Imaging. +- Spherical harmonics for mechanical motion modelling. +- Riemannian geometry on Shapes and diffeomorphisms for fMRI. +- Manifolds, Levi-Chivita connection and curvature tensors. +- Differential forms and fibre bundles with examples. +- Navier-Stokes equations and viscous flow. +- Geometric algebra, exterior product and quaternions. +- Graph convolution and continuous Laplace operators, diffusion models. +- Homology and cohomology, differential forms for model ensembling. ### Labworks -Two personal labworks on video signals include the problem statement and the computational experiment. The delivery is a two-page report with the problem and experimental results, a code and a talk. + +Two personal labworks on video signals include the problem statement and the computational experiment. The delivery is a two-page report with the problem and experimental results, a code and a talk. ### Grading + Questionnaires during lectures (3), two labworks (2+2), the final exam: topics and problems with discussion (3). ### Prerequisites + Algebra, analysis and physics at the postgraduate level. diff --git a/_i18n/en/_course/software_engineering_data_analysis.md b/_i18n/en/_course/software_engineering_data_analysis.md index 5fb611ed..3b183f8c 100755 --- a/_i18n/en/_course/software_engineering_data_analysis.md +++ b/_i18n/en/_course/software_engineering_data_analysis.md @@ -1,24 +1,30 @@ ### About + The course covers the development of data processing systems and machine learning. -* How to bring the developed model into production? -* What should I do to work together on high-tech software? -* How not to lose previously achieved research results? + +- How to bring the developed model into production? +- What should I do to work together on high-tech software? +- How not to lose previously achieved research results? As a result of mastering the course, students acquire the skills of industrial development of machine learning algorithms, conducting repeatable experiments, using big data, testing and project execution processes in the field of machine learning. ### Syllabus -* Structuring data processing programs (CODE). -* Writing reliable code (CODE). -* System design and data storage in machine learning (DATA) systems. -* Processes and types of work in the Data Analysis Project (PROC). -* Ensuring repeatability of results (PROC). -* Testing of high-tech software (TEST). + +- Structuring data processing programs (CODE). +- Writing reliable code (CODE). +- System design and data storage in machine learning (DATA) systems. +- Processes and types of work in the Data Analysis Project (PROC). +- Ensuring repeatability of results (PROC). +- Testing of high-tech software (TEST). ### Labworks + Practical tasks during the course + course project. ### Grading + The final grade for the course is formed from the success of completing tasks during the semester - 10% for each task, and confirmation on an oral survey of ownership of each of the topics of the course (CODE, TEST, DATA, PROC) - 40% of the grade. ### Prerequisites + Python. diff --git a/_i18n/en/_people/aduenko_aa.md b/_i18n/en/_people/aduenko_aa.md index 82a566d3..11054779 100644 --- a/_i18n/en/_people/aduenko_aa.md +++ b/_i18n/en/_people/aduenko_aa.md @@ -1,3 +1,2 @@ -He graduated with honors from MIPT in 2015. He defended his Ph.D. dissertation on mutlimodel selection for classification problems in 2017, candidate of physical and mathematical sciences. +He graduated with honors from MIPT in 2015. He defended his Ph.D. dissertation on mutlimodel selection for classification problems in 2017, candidate of physical and mathematical sciences. He is an author of more than 15 scientific papers on Bayesian inference and data analysis. - diff --git a/_i18n/en/_people/beznosikov_an.md b/_i18n/en/_people/beznosikov_an.md deleted file mode 100644 index b48c4296..00000000 --- a/_i18n/en/_people/beznosikov_an.md +++ /dev/null @@ -1,11 +0,0 @@ -Short bio. - -He graduated from MIPT in TODO. He defended his Ph.D. dissertation on in TODO, candidate of physical and mathematical sciences. -He is an author of more than TODO scientific papers on . - -**Professional interests:** TODO. - - -### Publications -1. TODO -2. TODO diff --git a/_i18n/en/_people/dorin_dd.md b/_i18n/en/_people/dorin_dd.md new file mode 100644 index 00000000..2bd75a5f --- /dev/null +++ b/_i18n/en/_people/dorin_dd.md @@ -0,0 +1,4 @@ +He graduated with honors from MIPT in 2024 and is currently a master's student at the Intelligent Systems Department. He +has authored over 5 research papers in brain-computer interfaces, computer vision and optimization. + +**Professional interests:** Brain-Computer Interfaces, Computer Vision. diff --git a/_i18n/en/_people/firsov_sa.md b/_i18n/en/_people/firsov_sa.md new file mode 100644 index 00000000..3c63440a --- /dev/null +++ b/_i18n/en/_people/firsov_sa.md @@ -0,0 +1,3 @@ +He graduated with a bachelor's degree from MIPT and is currently studying for a master's degree at the Intelligent Systems Department. He is now publishing 3 research papers in machine learning and teaching in MIPT. + +**Professional interests:** Computer Vision, Agent Systems, LLM. diff --git a/_i18n/en/_people/kasyuk_va.md b/_i18n/en/_people/kasyuk_va.md new file mode 100644 index 00000000..aeaeed53 --- /dev/null +++ b/_i18n/en/_people/kasyuk_va.md @@ -0,0 +1,3 @@ +He graduated with a bachelor's degree from MIPT in 2025 and is currently studying for a master's degree at the Intelligent Systems Department. + +**Professional interests:** Generative Models, Reinforcement Learning, LLMs. diff --git a/_i18n/en/_people/kiselev_ns.md b/_i18n/en/_people/kiselev_ns.md new file mode 100644 index 00000000..b7cce346 --- /dev/null +++ b/_i18n/en/_people/kiselev_ns.md @@ -0,0 +1,3 @@ +He graduated with honors from MIPT in 2024 and is currently a master's student at the Intelligent Systems Department. He has authored over 6 research papers in computer vision and optimization. + +**Professional interests:** Generative AI, Computer Vision, Optimization. diff --git a/_i18n/en/_people/kreinin_mv.md b/_i18n/en/_people/kreinin_mv.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/en/_people/kreinin_mv.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/en/_people/morozov_ma.md b/_i18n/en/_people/morozov_ma.md new file mode 100644 index 00000000..054558cc --- /dev/null +++ b/_i18n/en/_people/morozov_ma.md @@ -0,0 +1,3 @@ +He graduated with honors from MIPT & Scoltech in 2022. He began his postgraduate studies at KAUST in 2023, focusing on 3D, Deep Learning, and Computer Vision under the supervision of Prof. Peter Wonka. + +**Professional interests:** Deep Generative Models, 3D Computer Vision. diff --git a/_i18n/en/_people/nikitina_ma.md b/_i18n/en/_people/nikitina_ma.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/en/_people/nikitina_ma.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/en/_people/panchenko_sk.md b/_i18n/en/_people/panchenko_sk.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/en/_people/panchenko_sk.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/en/_people/vladimirov_ea.md b/_i18n/en/_people/vladimirov_ea.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/en/_people/vladimirov_ea.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/en/_people/yakovlev_kd.md b/_i18n/en/_people/yakovlev_kd.md index 4f004415..61e30000 100644 --- a/_i18n/en/_people/yakovlev_kd.md +++ b/_i18n/en/_people/yakovlev_kd.md @@ -1,4 +1,3 @@ -He graduated from [Moscow Institute of Physics and Tecnhology](https://mipt.ru/english/) (MIPT) in 2024. -Since 2024 he is a postgraduate student in MIPT. +He graduated with honors from MIPT in 2024 and is currently a postgraduate student in at the Intelligent Systems Department. -**Professional interests:** TODO +**Professional interests:** Statistical learning theory. diff --git a/_i18n/en/_posts/2025-10-30-new-website.md b/_i18n/en/_posts/2025-10-30-new-website.md new file mode 100644 index 00000000..6cef2181 --- /dev/null +++ b/_i18n/en/_posts/2025-10-30-new-website.md @@ -0,0 +1,19 @@ +--- +layout: news +title: "New Website Design" +date: 2025-10-30 +excerpt: "We present our new website design, updated for better user experience and accessibility." +lang: en +important: false +--- + +Intelligent Systems Department upgraded its website to enhance user experience and accessibility. + +Key features are: + +1. News section for latest updates +2. Improved navigation menu +3. Mobile-friendly design +4. Landing page for new visitors +5. Templates for writing papers, report, and theses +6. Conferences deadlines calendar diff --git a/_i18n/en/_posts/2025-10-31-admission.md b/_i18n/en/_posts/2025-10-31-admission.md new file mode 100644 index 00000000..8d5b873c --- /dev/null +++ b/_i18n/en/_posts/2025-10-31-admission.md @@ -0,0 +1,10 @@ +--- +layout: news +title: "Admission" +date: 2025-10-31 +excerpt: "Interview will be held on November 1st at 13:00, online via Zoom." +lang: en +important: true +--- + +The Intelligent Systems Department will hold an admission interview on November 1st at 13:00, online via Zoom: [m1p.org/go_zoom](https://m1p.org/go_zoom). diff --git a/_i18n/en/about.md b/_i18n/en/about.md deleted file mode 100644 index d9cafead..00000000 --- a/_i18n/en/about.md +++ /dev/null @@ -1,59 +0,0 @@ -### Department of Intelligent Systems -Phystech School of Applied Mathematics and Informatics MIPT - -The base department graduates bachelors and masters in the direction 010900 "Applied Mathematics and Physics". Education at the department is in three specializations "Data Science", "Design and Organization of Intelligent Systems", "Information Retrieval and Machine Learning". The base organization is the Computing Center of the Federal Research Center “Informatics and Control” of the Russian Academy of Sciences. - -The base organization is the Computing Center of the Russian Academy of Sciences, the Federal Research Center "Informatics and Control" of the Russian Academy of Sciences. The founder is an academician of the Russian Academy of Sciences and an outstanding Russian mathematician, an expert in the field of mathematical methods of recognition, forecasting and data analysis [Konstantin Vladimirovich Rudakov](https://ru.wikipedia.org/wiki/Рудаков,_Константин_Владимирович). The department has been actively developing since 2003 within the scientific school of the academician of the Russian Academy of Sciences [Yuri Ivanovich Zhuravlev](https://ru.wikipedia.org/wiki/Журавлёв,_Юрий_Иванович_(математик)). A significant contribution to the development of the department was made by the professor of the Russian Academy of Sciences, Doctors of Physical and Mathematical Sciences. [K.V. Vorontsov](https://ru.wikipedia.org/wiki/Воронцов,_Константин_Вячеславович) and V.V. Strijov. - -### Teachers of the department -[20 researchers](/people/): professor of the Russian Academy of Sciences, doctors and candidates of sciences. Teachers are young candidates of sciences, graduates of the department Ph.D. [Alexander Aduenko](/people/aduenko_aa/index.html), Ph.D. [Oleg Bakhteev](/people/bakhteev_oy/index.html), Ph.D. [Roman Isachenko](/people/isachenko_rv/index.html), graduate student [Andrey Grabovoy](/people/grabovoy_av/index.html). The average age of the teachers is 35 years. - -### Areas of educational and scientific activities of the department -Machine learning; multivariate statistics; geometric methods of deep learning; model selection and neural network architectures; ensembles of models and generative neural networks; functional data analysis and analysis of spatio-temporal data. - -### Applied Research -Text analysis and topic modeling, image and video analysis, multivariate time series analysis, biomedical signal analysis, brain-computer interfaces. - -### Principles of Scientific Work -Openness of ideas, projects, results at all stages of study and research; continuous assessment of the quality of ideas and results; communication with the scientific community, updating according to the latest achievements. - -### Main courses -***Machine Learning***, read by K.V. Vorontsov, is the most famous and complete course in Russia, covering fundamental and modern topics of machine learning and data analysis. - -***My first scientific article: automation of scientific research***, read by V.V. Strijov, is a course that provides the basics for performing scientific research - from planning to presenting results. Each student chooses a personal project and receives a personal consultant and expert. For three months, the student prepares a scientific paper with theory and computational experiment. The results are presented at scientific conferences, articles are submitted to peer-reviewed journals. - -### Main courses ([programs](/course/)) -- Machine Learning -- Automation of scientific research -- Deep learning -- Bayesian model selection -- Forecasting methods -- Deep generative models -- Bayesian multimodeling -- Probabilistic topic modeling -- Natural language processing -- Data analysis in metric spaces -- Signal processing -- Bioinformatics -- Software engineering for data analysis -- Recommender systems - -### Scholarships -- [Scientific academic scholarship to them. K.V. Rudakova](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/Stipendia_im_Rudakova.pdf) is awarded to undergraduate and graduate students for academic and research excellence. Sponsored by Forexis Group. - -### Collaborative training programs -In 2019, the department organized a double degree and joint master's program at the University of Grenoble-Alpes. Master's students study in joint programs at the Paris Polytechnic School, the Skolkovo Institute of Science and Technology, the KAUST University of Science and Technology. Joint research is underway with laboratories UGA, INRIA, CNRS, Ecole Polytechnique, EPFL, Los-Alamos, CMU. -- [Master program in Operations Research, Combinatorics and Optimization](https://master-informatique.univ-grenoble-alpes.fr/main-menu/academic-program/operations-research-combinatorics-optimisation/operations-research-combinatorics-optimisation-79396.kjsp?RH=1467388092289), [MIPT page](https://mipt.ru/education/joint_programs/ecolepolytech/) -- [Master of Science in Informatics at Grenoble](https://master-informatique.univ-grenoble-alpes.fr/main-menu/academic-program/master-of-science-mosig/), [MIPT page]( https://mipt.ru/education/joint_programs/grenoble.php) -- [Cycle Ingeneur at Ecole Polytechnique](https://www.polytechnique.edu/admission-cycle-ingenieur/en), [MIPT website](https://mipt.ru/education/joint_programs/grenoble.php) - -### Internships -Since the beginning, the department has been actively cooperating with the base companies of the Forexis Group of Companies: Forexis, Antiplagiat, Antirutina, GoodfoCast, Labor Laboratory, Procompliance and participates in joint projects of Forexis Group with the companies MMFB, InterRAO, Yandex, Sberbank, Russian Railways, Samsung, LG. -- Forexis: [time series analysis, financial analytics, news flow analysis](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/Forecsys_Intern.pdf) -- Antiplagiat: [text analysis](https://www.antiplagiat.ru/) -- INRIA National Institute for Research in Digital Science and Technology: [Bioinformatics](https://team.inria.fr/nano-d/job-openings/) - -### Come and study with us and do research on machine learning! -- [About admission](/admission/) -- [Download the page about the department](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/Intelligent_Systems_MIPT.pdf) -- [Download the slides about the department](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/IS_Slides.pdf) diff --git a/_i18n/en/admission.md b/_i18n/en/admission.md index 6dea4023..1aa9598c 100644 --- a/_i18n/en/admission.md +++ b/_i18n/en/admission.md @@ -1,45 +1,198 @@ - - -**Admission format:** interview - -### Algorithm of admission, bachelors, 2nd year: - -1. A student fills in the [form](http://bit.ly/1lFrFha), -2. solves one of the following tasks, -3. makes an opinion about the work performed by the students of the department, -4. on the appointed date, makes a three-minute report on the task and on the topic or work of interest, -5. is waiting for the decision of the dean's office on the distribution to the department. - -### The interview procedure from the point of view of the department teachers: -1.Gathering the whole group of those wishing to enter the department, -2. Listen to a short report of each participant, - - "solving a test problem", - - "my goals for admission to the department" on the material of student works of the department, -3. Ask questions, look at the questionnaire, -4. Draw up a ranked list of applicants, publish [by the link here] and send it to the dean's office, close the reception. - -### The Master admission procedure: -1. A student fills the [form](http://bit.ly/1lFrFha), -2. sends a request to mlalgorithms at gmail -3. parts interview with - - BS thesis, - - topics and results of the students scientific works at the department, - - mathematics of the BS programme: algebra, analysis, probability (functional analysis and measure theory included) - -### Test problems (2022 and earlier) -[Link](http://www.machinelearning.ru/wiki/index.php?title=%D0%9F%D1%80%D0%BE%D0%B1%D0%BD%D1%8B%D0%B5_%D0%B7%D0%B0%D0%B4%D0%B0%D1%87%D0%B8) – the spring of 2023 will be published here - -### Check the your basic abilities, spring 2023 -Chapters 1, 2, 3 from the [Pen and Paper Exercises in Machine Learning by Michael U. Gutmann](https://arxiv.org/abs/2206.13446) - -### Tips for solving problems (these are just tips, not directions) -- A theoretical solution is more important than a practical one. -- Write the theory yourself (do not copy the material from the lectures). -- Visualize problem solving (freehand drawing is preferable to none). -- Put the results of the experiment on slides (do not show pynb). -- When discussing neural networks, keep in mind that for us they are not black boxes, but transparent ones. -- Take these, or past, or your tasks - which is interesting to you. - -### Report topics for discussion -[Link](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%9F%D1%80%D0%B8%D0%B5%D0%BC_%D1%81%D1%82%D1%83%D0%B4%D0%B5%D0%BD%D1%82%D0%BE%D0%B2#.D0.A1.D0.BF.D0.B8.D1.81.D0.BE.D0.BA_.D1.82.D0.B5.D0.BC_.D0.B4.D0.BB.D1.8F_.D0.BA.D1.80.D0.B0.D1.82.D0.BA.D0.B8.D1.85_.D0.B4.D0.BE.D0.BA.D0.BB.D0.B0.D0.B4.D0.BE.D0.B2) +## Admission to the Department + +On this page, you will find information about the admission process to the Intelligent Systems Department at MIPT, including details for individual course attendees, the interview procedure for undergraduates, the master's program admission process, and research work at the department. + +**For Individual Course Attendees** + +1. Come, listen, and participate. +2. All information about current courses is available in the [Telegram channel]({{site.telegram}}). +3. Grade sheets for the department are processed through the dean's office—submit them there. +4. Courses require preparation, therefore: + - confirm with instructors that you can join the course, + - during the first few weeks, determine whether you will be able to pass the course. +5. Find out what is required to pass the course. + +### Admission Process for 2nd-3rd Year Undergraduates + +1. The student fills out the [application form](http://bit.ly/1lFrFha), +2. Solves one of the trial tasks listed below (fourth-year students present their thesis work), +3. Forms an opinion about the research conducted by department students ([Theses]({{ site.baseurl }}/materials/thesis), [Research Reports]({{ site.baseurl }}/materials/nir)), +4. On the scheduled date, gives a three-minute presentation about the task and about a topic or project that interested them, +5. Receives the department's decision that same evening, +6. Awaits the dean's office directive on department assignment. + + + +### Trial Tasks Fall 2025 and Earlier + +#### Fall 2025 + +
+

Task 64

+

+ Visualize the Gerchberg–Saxton algorithm for two-dimensional images. + Explain the two-dimensional Fourier transform, the source and target spaces, and the convergence within them. +

+
+ +
+

Task 63

+

+ Explain methods for the numerical solution of ordinary differential equations with illustrations using real measurement data. It is desirable to include the Adjoint State Method. +

+
+ +
+

Task 62

+

+ Explain the Galerkin method using an example with real data. Replace the linear model with a two-layer neural network. Show the difference in the solution. Visualize the data and the model. +

+
+ +
+

Task 61

+

+ Explain the finite element method with an example using real data (elasticity equation, Poisson's equation, other partial differential equations of your choice). Visualize different approaches, for linear models and neural networks. +

+
+ +
+

Task 60

+

+ Illustrate the dimensionality reduction algorithm in the Galerkin method for solving the Navier-Stokes equation with an illustration using real or synthetic data. +

+
+ +
+

Task 59

+

+ Illustrate the dimensionality reduction algorithm on two-dimensional computed tomography data, using a linear model (and a neural network by choice). +

+
+ +
+

Task 58

+

+ Explain forecasting a segment of a time series using the method of Singular Spectrum Analysis (Russian version). Analyze the original dimension of the Hankel matrix and its reduced dimension. +

+
+ +
+

Task 57

+

+ Explain how higher-order Fourier transforms (with tensor data representation) differ from the one-dimensional Fourier transform. Illustrate using a low-resolution animation (or similar data; with forward and inverse transforms including quality reduction). +

+
+ +
+

Task 56

+

+ Compare classical methods for the numerical solution of partial differential equations (elliptic, parabolic, hyperbolic) and neural network approximations of solutions using real data. +

+
+ +
+

Task 55

+

+ Given a smartphone IMU time series (accelerometer, gyroscope). The phone is placed on a person's chest. Propose an algorithm for decomposing almost-periodic oscillations (pulse, respiration, random movements). +

+
+ +
+

Task 54

+

+ Given two time series, determine if they are causally linked (causal inference) using the Convergent Cross Mapping method. Analyze the dimensions of the spaces. +

+
+ +#### Tasks from Previous Years + +[Tasks from previous years](http://www.machinelearning.ru/wiki/index.php?title=%D0%9F%D1%80%D0%BE%D0%B1%D0%BD%D1%8B%D0%B5_%D0%B7%D0%B0%D0%B4%D0%B0%D1%87%D0%B8) can also be used for the presentation. + +### Tips for Solving Tasks (these are suggestions, not requirements) + +- Theoretical solutions are more important than practical ones. +- Write the theory yourself (do not copy lecture materials). +- Visualize your solutions (a hand-drawn diagram is preferable to no diagram at all). +- Present experimental results on slides (do not show Jupyter notebooks). +- When discussing neural networks, keep in mind that for us they are not black boxes but transparent systems. +- Choose these tasks, past tasks, or your own—whatever interests you most. + +### List of Topics for Discussion + +[Compiled in the Topics List section on this page](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%9F%D1%80%D0%B8%D0%B5%D0%BC_%D1%81%D1%82%D1%83%D0%B4%D0%B5%D0%BD%D1%82%D0%BE%D0%B2#.D0.A1.D0.BF.D0.B8.D1.81.D0.BE.D0.BA_.D1.82.D0.B5.D0.BC_.D0.B4.D0.BB.D1.8F_.D0.BA.D1.80.D0.B0.D1.82.D0.BA.D0.B8.D1.85_.D0.B4.D0.BE.D0.BA.D0.BB.D0.B0.D0.B4.D0.BE.D0.B2) + +### Selection Results + +- Published the day after selection in the department's [Telegram channel]({{site.telegram}}). + +## Master's Program Admission Procedure + +1. The student fills out the [application form](http://bit.ly/1lFrFha), +2. We gather candidates wishing to join the department upon their request, +3. We review the application, thesis work, ask about their opinion on topics and student research at the department, and ask questions from the [mathematical section](https://arxiv.org/abs/2206.13446) of the bachelor's program (Sections 1, 2, 3 from "Pen and Paper Exercises in Machine Learning" by Michael U. Gutmann) + +The purpose of the interview is to understand: + +1. What contribution the student will make to the department's research, +2. Whether the student's qualifications match the level of planned master's dissertations. + +## Research Work at the Department + +Your research qualifications are your primary goal at the department. The department focuses on the mathematical foundations of machine learning. This means that your work focuses on developing theoretical methods. You obtain theoretical results. Practical applications to illustrate your results in computational experiments may be arbitrary. + +Scientific collaboration and exchange of ideas are the foundation of research work. Do not hesitate to write to researchers and tell them about yourself, your results, and your plans. The purpose of your research advisor is to show you the right direction for research, provide a topic, and formulate a problem in general terms. Keep in mind that the advisor works in their own field. How can you learn about their field? Go to [scholar.google.com](https://scholar.google.com/scholar?q=Vadim+Strijov&hl=en&as_sdt=0%2C5&as_ylo=2022&as_yhi=2019), enter the advisor's name, and review their work from recent years. Ask your advisor for a research task. + +Requirements for a research advisor: + +1. Doctor of Science (D.Sc.) or Candidate of Science (Ph.D.), +2. Works in the department's field and maintains contact with the department. + +The department cannot assign you a research advisor. You must find one through communication and agreement on joint work. When searching for research advisors, tell them about yourself: your qualifications, achievements, research papers, and plans. + +**Tip:** Look for research advisors in research groups. If you are interested in: + +- Topic modeling, information retrieval, news analysis—this is the group of Prof. Konstantin Vyacheslavovich Vorontsov, +- Mathematics, optimization, control, mathematical modeling—this is the group of Prof. Alexander Vladimirovich Gasnikov, +- Technologies for creating artificial intelligence systems, image and video analysis—this is the group of Prof. Ivan Alekseevich Matveev, +- Generative models, geometric deep learning, model selection, signal analysis—this is the group of Prof. Vadim Viktorovich Strijov, +- Pure and discrete mathematics, advanced combinatorics—this is the group of Prof. Andrey Mikhailovich Raigorodsky. + +Find members of these research groups. Look at the topics of their recent research papers. Compile a list of co-authors. Review the attached PDF. Write to potential advisors. Important tip: Connect with students and graduate students in your field. Ask them how they organize their work with research advisors. + +For quick presentation of initial results, try to participate in student conferences ([example](https://conf.mipt.ru)). + +### What You Need to Do + +1. Look at who has been a successful research advisor: + - [Thesis works](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%A1%D1%82%D1%83%D0%B4%D0%B5%D0%BD%D1%82%D1%8B), + - [Research reports and format](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%9E%D1%82%D1%87%D0%B5%D1%82%D1%8B_%D0%9D%D0%98%D0%A0), + - [Department faculty](http://is-mipt.site), + - [Bachelor's thesis defenses](https://www.youtube.com/watch?v=mmAacGSUvPQ), + - [Master's thesis defenses](https://www.youtube.com/watch?v=f4C9U59krTE), + - [Ph.D. dissertation defenses](https://www.youtube.com/playlist?list=PLk4h7dmY2eYGO1lczVHclXnv0f-CvUkXO). +2. Consult with students and graduate students. Read the [guidelines](http://www.machinelearning.ru/wiki/index.php?title=%D0%9D%D0%B0%D1%83%D1%87%D0%BD%D0%BE-%D0%B8%D1%81%D1%81%D0%BB%D0%B5%D0%B4%D0%BE%D0%B2%D0%B0%D1%82%D0%B5%D0%BB%D1%8C%D1%81%D0%BA%D0%B0%D1%8F_%D1%80%D0%B0%D0%B1%D0%BE%D1%82%D0%B0_%28%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%86%D0%B8%D0%B8%29). +3. Find a research advisor (matching your thinking style and interests). +4. Ask them to **contact the department** and approve your research topic. +5. Begin working with them and present the results during exam week at the beginning of the session. +6. Reporting format: [paper, presentation, code]({{ site.baseurl }}/materials/nir). + +### Timeline + +1. Third-year students search for research advisors during the spring semester and report this at the research credit. +2. Fifth-year students have a research advisor at the beginning of the fall semester (we ask about plans). +3. Graduate students have publications with their research advisor. + +**Tip:** Changing your research advisor and topic at any time is normal—you are developing and priorities change. It is advisable to complete projects so you have something to show. Working with multiple research advisors on different topics is wonderful (if you can manage it). Working in teams is excellent—your personal contribution is what matters. diff --git a/_i18n/en/conferences.md b/_i18n/en/conferences.md index 3d7b8b00..05d5ce0d 100644 --- a/_i18n/en/conferences.md +++ b/_i18n/en/conferences.md @@ -1,668 +1,775 @@ -# Conferences & Journals on scientific topics of the department +## Conferences & Journals -The conferences mainly are retrieved from here http://www.guide2research.com/topconf/ (+ CORE2021: https://www.core.edu.au/conference-portal + some Russian and conferences well known by me). +This page contains upcoming deadlines for top-tier machine learning conferences, and a comprehensive list of conferences and journals relevant to our department's research areas. + +
+

Conferences Deadlines

+

Stay up-to-date with the most important events in the field!

+
+ {% assign today = site.time | date: '%s' %} + + {% comment %} Collect conferences with their effective deadlines and timestamps {% endcomment %} + {% assign conference_data = "" | split: "" %} + + {% for conf in site.data.conferences.conferences %} + {% if conf.active == true %} + {% assign abstract_timestamp = conf.abstract_deadline | date: '%s' %} + {% assign submission_timestamp = conf.submission_deadline | date: '%s' %} + + {% comment %} Determine effective deadline for sorting {% endcomment %} + {% if conf.abstract_deadline and abstract_timestamp >= today %} + {% assign sort_timestamp = abstract_timestamp %} + {% else %} + {% assign sort_timestamp = submission_timestamp %} + {% endif %} + + {% comment %} Only include if has future deadline {% endcomment %} + {% if sort_timestamp >= today %} + {% comment %} Create a sortable string: "timestamp|conference_index" {% endcomment %} + {% assign conf_data = sort_timestamp | append: "|" | append: forloop.index0 %} + {% assign conference_data = conference_data | push: conf_data %} + {% endif %} + {% endif %} + {% endfor %} + + {% comment %} Sort by the timestamp (first part of string) {% endcomment %} + {% assign sorted_data = conference_data | sort %} + + {% if sorted_data.size == 0 %} +
+

No upcoming conference deadlines at the moment. Check back later!

+
+ {% endif %} + + {% assign upcoming_count = 0 %} + {% for data_item in sorted_data %} + {% assign data_parts = data_item | split: "|" %} + {% assign conf_index = data_parts[1] | plus: 0 %} + {% assign conf = site.data.conferences.conferences[conf_index] %} + {% comment %} Determine which deadline to use and check {% endcomment %} + {% assign abstract_timestamp = conf.abstract_deadline | date: '%s' %} + {% assign submission_timestamp = conf.submission_deadline | date: '%s' %} + + {% comment %} Determine the primary deadline (abstract if exists and hasn't passed, otherwise submission) {% endcomment %} + {% if conf.abstract_deadline and abstract_timestamp >= today %} + {% assign primary_deadline = conf.abstract_deadline %} + {% assign primary_deadline_timestamp = abstract_timestamp %} + {% assign deadline_type = "Abstract" %} + {% else %} + {% assign primary_deadline = conf.submission_deadline %} + {% assign primary_deadline_timestamp = submission_timestamp %} + {% assign deadline_type = "Submission" %} + {% endif %} + + {% comment %} Only show conferences with upcoming deadlines {% endcomment %} + {% if primary_deadline_timestamp >= today %} + {% assign upcoming_count = upcoming_count | plus: 1 %} + {% assign days_until = primary_deadline_timestamp | minus: today | divided_by: 86400 | plus: 1 %} + +
+

{{ conf.name }}

+ {{ conf.rank }} +
+

{{ conf.full_name }}

+
+ {% comment %} Show abstract deadline if it exists and hasn't passed {% endcomment %} + {% if conf.abstract_deadline and abstract_timestamp >= today %} +
+ Abstract Deadline + {{ conf.abstract_deadline | date: "%b %d, %Y" }} +
+ {% endif %} + {% comment %} Show submission deadline if different from abstract or if abstract has passed {% endcomment %} + {% if conf.submission_deadline != conf.abstract_deadline or abstract_timestamp < today %} +
+ Submission Deadline + {{ conf.submission_deadline | date: "%b %d, %Y" }} +
+ {% endif %} + {% if days_until <= 30 %} +
+ ⚠️ Only {{ days_until }} days left until {{ deadline_type | downcase }} deadline! +
+ {% endif %} +
+
+ 📅 Conference: {{ conf.conference_date | date: "%b %d, %Y" }} +
+
+ 📍 {{ conf.location }} +
+ + {% endif %} + {% endfor %} +
+
+ +Here we collect and list conferences and journals relevant to our department's research areas. The conferences mainly are retrieved from here http://www.guide2research.com/topconf/ (+ CORE2021: https://www.core.edu.au/conference-portal + some Russian and conferences well known by me). The journals are retrieved from here https://www.scimagojr.com/journalrank.php. References: + 1. https://tinyurl.com/bahleg-conf 2. https://tinyurl.com/bahleg-journals -## Conferences +Tap to expand full lists: + +### Conferences -|Conference name |Category |Conference program |URL |Rank|Rank system| -|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------|-----------------------------------------------------------------------------------|------------------------------------------------------------|----|-----------| -|SIGBOVIK |Specific | |http://sigbovik.org/ |- |- | -|ECIR : European Conference on Information Retrieval |IR/Mining |Demo, Industrial, Tutorials, Workshops |https://www.ecir2024.org/ |A |CORE2021 | -|SIGIR: International ACM SIGIR Conference on Research and Development in Information Retrieval |IR/Mining | |https://sigir-2024.github.io/ |A |CORE2021 | -|WWW: International World Wide Web Conferences |IR/Mining |Demo, StudentThesis / Doctor symposium, Tutorials, Workshops |https://www2024.thewebconf.org/ |A |CORE2021 | -|ESWC : Extended Semantic Web Conference |IR/Mining | |https://2024.eswc-conferences.org/ |A |CORE2021 | -|MSR : Mining Software Repositories |IR/Mining, Specific | |https://2024.msrconf.org/ |A |CORE2021 | -|WSDM : ACM International Conference on Web Search and Data Mining |IR/Mining | |https://www.wsdm-conference.org/2024/ |A |CORE2021 | -|PODS : ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems |IR/Mining |Demo, Industrial, Tutorials, Workshops |https://2024.sigmod.org/ |A |CORE2021 | -|RecSys : ACM Conference on Recommender Systems |IR/Mining |Tutorials, Workshops |https://recsys.acm.org/recsys24/ |A |CORE2021 | -|EDBT : International Conference on Extending Database Technology |IR/Mining |StudentThesis / Doctor symposium, Workshops |https://edbt.org/ |A |CORE2021 | -|DASFAA : International Conference on Database Systems for Advanced Applications |IR/Mining | |https://www.dasfaa2024.org/ |B |CORE2021 | -|SSBSE : International Conference on Search based Software Engineering |IR/Mining | |https://ssbse.info/ |B |CORE2021 | -|UMAP : International Conference on User Modelling, Adaptation, and Personalization |IR/Mining, Specific | |https://www.um.org/umap2024/ |B |CORE2021 | -|Pacific Asia Conference on Language, Information and Computation |IR/Mining | | |B |CORE2021 | -|International Conference on Formal Ontology in Information Systems |IR/Mining, Specific | | |B |CORE2021 | -|ADBIS : Advances in Databases and Information Systems |IR/Mining |StudentThesis / Doctor symposium, Tutorials, Workshops |https://conferences.sigappfr.org/adbis2024/ |B |CORE2021 | -|WISE : International Conference on Web Information Systems Engineering |IR/Mining | |https://wise2024-qatar.com/ |B |CORE2021 | -|Workshop on Logic, Language, Information and Computation |IR/Mining, NLP | |https://wollic2024.inf.unibe.ch/ |B |CORE2021 | -|EKAW : Knowledge Engineering and Knowledge Management |IR/Mining | | |B |CORE2021 | -|TPDL : International Conference on Theory and Practice of Digital Libraries |IR/Mining | | |B |CORE2021 | -|International Conference on Knowledge-Based and Intelligent Information and Engineering Systems |IR/Mining |Workshops |http://kes2024.kesinternational.org/ |B |CORE2021 | -|Asian Conference on Intelligent Information and Database Systems |IR/Mining | |https://aciids.pwr.edu.pl/2024/ |B |CORE2021 | -|ADMA : International Conference on Advanced Data Mining and Applications |IR/Mining | |https://adma2024.github.io/ |B |CORE2021 | -|WI : IEEE/WIC/ACM International Conference on Web Intelligence |IR/Mining |SpecialSession, Workshops | |B |CORE2021 | -|International Symposium on Computer and Information Sciences |IR/Mining | |https://www.iscsic.org/ |C |CORE2021 | -|European-Japanese Conference on Information Modelling and Knowledge Bases |IR/Mining | |https://ejc2024.ds.musashino-u.ac.jp/ |C |CORE2021 | -|International Conference on Information Technology and Applications |IR/Mining |SpecialSession, Workshops |https://www.icita.world/#/ |C |CORE2021 | -|International Conference on Legal Knowledge and Information Systems |IR/Mining, Specific | | |C |CORE2021 | -|Asia Information Retrieval Symposium |IR/Mining | | |C |CORE2021 | -|TREC |IR/Mining, NLP | | |- |- | -|ASONAM : International Conference on Advances in Social Network Analysis and Mining |IR/Mining | | |- |- | -|IEEE International Conference on Information and Automation |IR/Mining, ML/CS, Specific | | |- |- | -|WebSci : ACM on Web Science Conference |IR/Mining |Tutorials, Workshops |https://websci24.org/ |- |- | -|ISWC : International Semantic Web Conference |IR/Mining |Tutorials, Workshops | |- |- | -|BTAS : IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS) |IR/Mining, Specific | | |- |- | -|Russir |IR/Mining, NLP | | |- |- | -|Statistical and Scientific Database Management |IR/Mining | |https://ssdbm.org/2024/ |- |- | -|International Conference on Information and Knowledge Engineering |IR/Mining, Specific | | |- |- | -|International Conference on the Theory of Information Retrieval |IR/Mining | | |- |- | -|IJCB : International Joint Conference on Biometrics |IR/Mining, Specific |Demo, StudentThesis / Doctor symposium, Tutorials | |- |- | -|CHIIR : Conference on Human Information Interaction and Retrieval |IR/Mining | |https://chiir2024.github.io/ |- |- | -|Conference on Information Sciences and Systems |IR/Mining | |https://ee-ciss.princeton.edu/ |- |- | -|International Baltic Conference on Databases and Information Systems |IR/Mining | | |- |- | -|ICWSM : International Conference on Web and Social Media |IR/Mining | |https://www.icwsm.org/2024/index.html/ |- |- | -|BigMM : IEEE International Conference on Multimedia Big Data |IR/Mining | | |- |- | -|SemEval : International Workshop on Semantic Evaluation |CV, IR/Mining, NLP, Signal | |https://semeval.github.io/SemEval2024/ |- |- | -|AVSS : IEEE International Conference on Advanced Video and Signal-Based Surveillance |Signal | |https://zinc.cse.buffalo.edu/ubmdfl/AVSS2024/index.php |B |CORE2021 | -|MMSP : IEEE Workshop on Multimedia Signal Processing |Signal |Demo, SpecialSession | |B |CORE2021 | -|International Conference on Image and Signal Processing |Signal | |https://csita2024.org/ispr/index |C |CORE2021 | -|IEEE Symposium on Computational intelligence for Multimedia Signal and Vision Processing |Signal | | |C |CORE2021 | -|DCASE : Detection and Classification of Acoustic Scenes and Events |Signal |Contests, Workshops | |- |- | -|ISMIR : International Society for Music Information Retrieval Conference |IR/Mining, Signal, Specific|Tutorials |https://ismir2024.ismir.net/ |- |- | -|EUSIPCO : European Signal Processing Conference |Signal |Tutorials, Workshops |https://eusipcolyon.sciencesconf.org/ |- |- | -|International Conference on Robotics, Vision, Signal Processing and Power Applications (was ROVPIA) |Signal, Specific | | |- |- | -|ICASSP: International Conference on Acoustics, Speech and Signal Processing |Signal | |https://2024.ieeeicassp.org/ |- |- | -|SLT : IEEE Spoken Language Technology Workshop |Signal |Contests, Demo, Hackaton, Workshops | |- |- | -|ACM Symposium on Eye Tracking Research and Applications |CV, Signal, Specific | |https://etra.acm.org/2024/ |- |- | -|International Conference on Advanced Technologies For Signal & Image Processing |Signal | | |- |- | -|WASPAA : IEEE Workshop on Applications of Signal Processing to Audio and Acoustics |Signal | | |- |- | -|SPAWC |Signal | |https://spawc2024.org/ |- |- | -|APSIPA : Asia-Pacific Signal and Information Processing Association Annual Summit and Conference |Signal | | |- |- | -|SSP : IEEE Statistical Signal Processing Workshop |Signal | | |- |- | -|INTERSPEECH: Conference of the International Speech Communication Association |Signal | |https://interspeech2024.org/ |- |- | -|MIPR : IEEE Conference on Multimedia Information Processing and Retrieval |IR/Mining, Signal |Tutorials, Workshops | |- |- | -|ACSSC : Asilomar Conference on Signals, Systems and Computers |ML/CS, Signal | | |- |- | -|WCSP : International Conference on Wireless Communications and Signal Processing |Signal | | |- |- | -|SAM : IEEE Sensor Array and Multichannel Signal Processing Workshop |Signal | |https://2024.ieeesam.org/ |- |- | -|ICME: International Conference on Multimedia and Expo |CV, NLP, Signal | |https://2024.ieeeicme.org/ |A |CORE2021 | -|EACL : Conference of the European Chapter of the Association for Computational Linguistics |NLP | |https://2024.eacl.org/ |A |CORE2021 | -|CoNLL: Conference on Computational Natural Language Learning |NLP | | |A |CORE2021 | -|ACL: Annual Meeting of the Association for Computational Linguistics |NLP | |https://2024.aclweb.org/ |A |CORE2021 | -|EMNLP: Conference on Empirical Methods in Natural Language Processing |NLP |TBA | |A |CORE2021 | -|COLING: International Conference on Computational Linguistics |NLP |Tutorials, Workshops |https://lrec-coling-2024.org/ |A |CORE2021 | -|NAACL: North American Chapter of the Association for Computational Linguistics |NLP |Demo, Industrial, Workshops |https://2024.naacl.org/ |A |CORE2021 | -|SIGDIAL : Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL) |NLP |SpecialSession |https://2024.sigdial.org/ |B |CORE2021 | -|IJCNLP : International Joint Conference on Natural Language Processing (IJCNLP) |NLP |Tutorials, Workshops | |B |- | -|DAS : IAPR International Workshop on Document Analysis Systems |NLP |SpecialSession | |B |CORE2021 | -|NLDB : International Conference on Applications of Natural Language to Information Systems |NLP | |https://nldb2024.di.unito.it/ |C |CORE2021 | -|LREC : International Conference on Language Resources and Evaluation (LREC) |NLP, Signal | |https://lrec-coling-2024.org/ |C |CORE2021 | -|Dialogue |NLP |Contests |http://www.dialog-21.ru/ |- |- | -|CLEF : International Conference of the Cross-Language Evaluation Forum for European Languages |CV, IR/Mining, NLP, Signal | |https://clef2024.clef-initiative.eu/ |- |- | -|SEM : Joint Conference on Lexical and Computational Semantics |NLP | |https://sites.google.com/view/starsem2024 |- |- | -|International Conference on Recent Advances in Natural Language Processing |NLP |Tutorials, Workshops | |- |- | -|AINL |NLP | | |- |- | -|IROS: International Conference on Intelligent Robots and Systems |CV |Tutorials, Workshops | |A |CORE2021 | -|ACMMM: ACM Multimedia |CV, NLP, Signal |Demo, StudentThesis / Doctor symposium, Workshops | |A |CORE2021 | -|ICCV: International Conference on Computer Vision |CV |TBA | |A |CORE2021 | -|ECCV: European Conference on Computer Vision |CV | |https://eccv2024.ecva.net/ |A |CORE2021 | -|MICCAI : Medical Image Computing and Computer Assisted Intervention |CV, Specific | |http://www.miccai.org/ |A |CORE2021 | -|ICDAR : International Conference on Document Analysis and Recognition |CV, IR/Mining, NLP | |https://icdar2024.net/ |A |CORE2021 | -|WACV: Winter Conference on Applications of Computer Vision |CV | |https://wacv2024.thecvf.com/ |A |CORE2021 | -|CVPR: IEEE Conference on Computer Vision and Pattern Recognition |CV |Tutorials, Workshops |https://cvpr.thecvf.com/ |A |CORE2021 | -|ICMR: ACM International Conference on Multimedia Retrieval |CV, IR/Mining, NLP, Signal | |http://icmr2024.org/ |B |CORE2021 | -|Advanced Concepts for Intelligent Vision Systems |CV | | |B |CORE2021 | -|ICIP: International Conference on Image Processing |CV |Demo, SpecialSession, Tutorials, Workshops |https://2024.ieeeicip.org/ |B |CORE2021 | -|Image and Vision Computing Conference |CV | | |B |CORE2021 | -|ACCV: Asian Conference on Computer Vision |CV |Demo, StudentThesis / Doctor symposium, Tutorials, Workshops |https://accv2024.org/ |B |CORE2021 | -|FG : IEEE International Conference on Automatic Face & Gesture Recognition |CV | |https://fg2024.ieee-biometrics.org/ |C |CORE2021 | -|International Conference on Control, Automation, Robotics and Vision |CV, Specific | | |C |CORE2021 | -|International Conference on Computer Vision Systems |CV |Tutorials, Workshops | |C |CORE2021 | -|International Conference on Machine Vision |CV |SpecialSession | |C |CORE2021 | -|BMVC: British Machine Vision Conference |CV |Workshops | |- |- | -|MLMI : International Workshop on Machine Learning in Medical Imaging |CV | | |- |- | -|3DV : International Conference on 3D Vision |CV |Demo, Tutorials |https://3dvconf.github.io/2024/ |- |- | -|ISBI : IEEE International Symposium on Biomedical Imaging |CV, Specific |SpecialSession, Tutorials |https://biomedicalimaging.org/2024/ |- |- | -|International Conference on Computer Vision and Graphics |CV | | |- |- | -|International Machine Vision and Image Processing Conference |CV |Workshops | |- |- | -|Machine Vision Applications |CV | | |- |- | -|International Conferences in Central Europe on Computer Graphics, Visualization and Computer Vision |CV | | |- |- | -|NeurIPS: Neural Information Processing Systems |ML/CS |BestPaperAward, Demo, Industrial, StudentPaper, Tutorials, Workshops |https://nips.cc/Conferences/2023 |A |CORE2021 | -|IJCAI: International Joint Conference on Artificial Intelligence |ML/CS | |https://ijcai24.org/ |A |CORE2021 | -|ECMLPKDD: European Conference on Machine learning and knowledge discovery in databases |IR/Mining, ML/CS |Tutorials, Workshops |https://2024.ecmlpkdd.org/ |A |CORE2021 | -|ICML: International Conference on Machine Learning |ML/CS | |https://icml.cc/Conferences/2024 |A |CORE2021 | -|PAKDD: Pacific-Asia Conference on Knowledge Discovery and Data Mining |IR/Mining, ML/CS |TBA |https://pakdd2024.org/ |A |CORE2021 | -|SIGKDD : ACM SIGKDD International Conference on Knowledge discovery and data mining |IR/Mining, ML/CS | |https://kdd.org/kdd2024/ |A |CORE2021 | -|LAK : International Conference on Learning Analytics And Knowledge |IR/Mining, ML/CS |StudentThesis / Doctor symposium |https://www.solaresearch.org/events/lak/lak24/ |A |CORE2021 | -|ICLR: International Conference on Learning Representations |ML/CS |TBA |https://iclr.cc/Conferences/2024 |A |CORE2021 | -|ICDE : International Conference on Data Engineering Workshops |ML/CS | |https://icde2024.github.io/ |A |CORE2021 | -|CIKM: ACM International Conference on Information and Knowledge Management |IR/Mining, ML/CS | |https://www.cikm2024.org/ |A |CORE2021 | -|European Conference on Artificial Intelligence |ML/CS |Tutorials, Workshops |https://www.ecai2024.eu/ |A |CORE2021 | -|IEEE International Conference on Data Science and Advanced Analytics |ML/CS |Tutorials |https://conferences.sigappfr.org/dsaa2023/ |A |CORE2021 | -|AISTATS: International Conference on Artificial Intelligence and Statistics |ML/CS | |https://aistats.org/aistats2024/ |A |CORE2021 | -|LICS : IEEE Symposium on Logic in Computer Science |ML/CS, Specific | |https://lics.siglog.org/lics24/ |A |CORE2021 | -|CIDR : Conference on Innovative Data Systems Research |ML/CS | |http://www.cidrdb.org/cidr2024/index.html |A |CORE2021 | -|SDM : SIAM International Conference on Data Mining (SDM) |ML/CS | |https://www.siam.org/conferences/cm/conference/sdm24 |A |CORE2021 | -|KR: International Conference on Principles of Knowledge Representation and Reasoning |IR/Mining, ML/CS |StudentThesis / Doctor symposium, Tutorials, Workshops |https://kr.org/KR2024/ |A |CORE2021 | -|SODA : ACM SIAM Symposium on Discrete Algorithms |ML/CS | |https://www.siam.org/conferences/cm/conference/soda24 |A |CORE2021 | -|ICDMW : IEEE International Conference on Data Mining |ML/CS |Tutorials, Workshops |https://www.cloud-conf.net/icdm2023/ |A |CORE2021 | -|UAI: Conference on Uncertainty in Artificial Intelligence |ML/CS | |https://www.auai.org/uai2024/ |A |CORE2021 | -|Logics in Artificial Intelligence, European Conference |ML/CS, Specific | | |A |CORE2021 | -|COLT: Conference on Learning Theory |ML/CS | |https://learningtheory.org/colt2024/ |A |CORE2021 | -|SIGMOD : ACM SIGMOD International Conference on Management of Data |ML/CS |TBA |https://2024.sigmod.org/ |A |CORE2021 | -|STOC : ACM Symposium on Theory of Computing |ML/CS, Specific | |http://acm-stoc.org/stoc2024/ |A |CORE2021 | -|AAAI: Association for the Advancement of Artificial Intelligence |ML/CS | |https://aaai.org/aaai-conference/ |A |CORE2021 | -|International Conference on Artificial Intelligence in Education |ML/CS, Specific | |https://www.aied2023.org/ |A |CORE2021 | -|ICPR : International Conference on Pattern Recognition |ML/CS | |http://www.icprs.org/ |B |CORE2021 | -|FUZZ : IEEE International Conference on Fuzzy Systems |ML/CS | | |B |CORE2021 | -|International Conference on Tools with Artificial Intelligence |ML/CS | | |B |CORE2021 | -|Australasian Joint Conference on Artificial Intelligence |ML/CS |Tutorials, Workshops | |B |CORE2021 | -|Educational Data Mining |IR/Mining, ML/CS, Specific | |https://educationaldatamining.org/edm2024/ |B |CORE2021 | -|International Conference on Integration of Artificial Intelligence and Operations Research Techniques in Constraint Programming for Combinatorial Optimization Problems|ML/CS | |https://sites.google.com/view/cpaior2024 |B |CORE2021 | -|Big Data : IEEE International Conference on Big Data |IR/Mining, ML/CS |SpecialSession, Tutorials, Workshops |https://bigdataieee.org/BigData2024/ |B |CORE2021 | -|DCC : Data Compression Conference |ML/CS, Specific | |https://www.cs.brandeis.edu/~dcc/index.html |B |CORE2021 | -|International Conference on Scientific and Statistical Data Base Management |ML/CS | |https://ssdbm.org/2024/ |B |CORE2021 | -|Web and Big Data |IR/Mining, ML/CS |Workshops | |B |CORE2021 | -|Pacific Rim International Conference on Artificial Intelligence |ML/CS |Tutorials, Workshops | |B |CORE2021 | -|IFIP WG 11.3 Working Conference on Data and Applications Security (also known as DBSEC) |ML/CS, Specific | | |B |CORE2021 | -|Australian Data Mining Conference |IR/Mining, ML/CS |StudentThesis / Doctor symposium, Tutorials, Workshops | |B |CORE2021 | -|SAC : ACM Symposium on Applied Computing |ML/CS | |http://www.sigapp.org/sac/sac2024/ |B |CORE2021 | -|International Conference on Agents and Artificial Intelligence |ML/CS |Demo, Panel, SpecialSession, StudentThesis / Doctor symposium, Tutorials, Workshops|https://icaart.scitevents.org/ |B |CORE2021 | -|Artificial Intelligence in Medicine in Europe |ML/CS, Specific | |https://www.aimedicine.info/aime24/ |B |CORE2021 | -|European Symposium on Artificial Neural Networks |ML/CS | |https://www.esann.org/ |B |CORE2021 | -|SMC : IEEE International Conference on Systems, Man and Cybernetics |ML/CS |Tutorials, Workshops |https://ieeesmc2024.org/ |B |CORE2021 | -|International Conference on Modelling Decisions for Artificial Intelligence |ML/CS | |http://www.mdai.cat/mdai2024/ |B |CORE2021 | -|International Conference on Neural Information Processing |ML/CS |Tutorials, Workshops | |B |CORE2021 | -|Intelligent Data Analysis |ML/CS | |https://ida2024.org/ |B |CORE2021 | -|IV : IEEE Intelligent Vehicles Symposium |ML/CS, Specific | |https://2024.ieee-iv.org/ |B |CORE2021 | -|IJCNN: International Joint Conference on Neural Networks |ML/CS | | |B |CORE2021 | -|Data Warehousing and Knowledge Discovery |IR/Mining, ML/CS |Workshops |https://www.dexa.org/dawak2024 |B |CORE2021 | -|CEC : IEEE Congress on Evolutionary Computation |ML/CS, Specific | | |B |CORE2021 | -|ISIT : IEEE International Symposium on Information Theory |ML/CS | |https://2024.ieee-isit.org/home |B |CORE2021 | -|International Conference on Intelligent Data Engineering and Automated Learning |ML/CS, Specific |SpecialSession |https://ideal2023.uevora.pt/ |C |CORE2021 | -|EURO |ML/CS | |https://euro2024cph.dk/ |C |CORE2021 | -|Artificial Intelligence Applications and Innovations |ML/CS | |https://ifipaiai.org/ |C |CORE2021 | -|International Symposium on Artificial Life and Robotics |ML/CS | |https://isarob.org/symposium/ |C |CORE2021 | -|International FLINS Conference on Robotics and Artificial Intelligence (was International Fuzzy Logic and Intelligent technologies in Nuclear Science Conference) |ML/CS | | |C |CORE2021 | -|International Conference on Engineering Applications of Neural Networks |ML/CS | |https://eannconf.org/2024/ |C |CORE2021 | -|IEEE/ACM International Conference on Big Data Computing, Applications and Technologies |ML/CS |Workshops |https://bdcat-conference.org/ |C |CORE2021 | -|IEEE Symposium on Computational Intelligence and Data Mining |ML/CS |Workshops | |C |CORE2021 | -|International Conference on Internet of Things, Big Data and Security |ML/CS |Demo, Panel, SpecialSession, Tutorials, Workshops |https://iotbds.scitevents.org/ |C |CORE2021 | -|International Symposium on Neural Networks |ML/CS | |https://conference.cs.cityu.edu.hk/isnn/ |C |CORE2021 | -|FUSION : International Conference on Information Fusion |ML/CS | | |C |CORE2021 | -|International Conference on Machine Learning and Applications |ML/CS |SpecialSession |https://www.icmla-conference.org/icmla24/ |C |CORE2021 | -|International Cross-Domain Conference for Machine Learning and Knowledge Extraction |IR/Mining, ML/CS, NLP |SpecialSession | |C |CORE2021 | -|ICANN: International Conference on Artificial Neural Networks |ML/CS | |https://e-nns.org/icann2024/ |C |CORE2021 | -|International Conference on Artificial Intelligence and Law |ML/CS, Specific | | |C |CORE2021 | -|International Conference on Data Science, Technology and Applications |ML/CS |TBA |https://data.scitevents.org/ |C |CORE2021 | -|International Conference on the Statistical Analysis of Textual Data |ML/CS, NLP | | |C |CORE2021 | -|International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing |ML/CS |SpecialSession, Workshops |https://acisinternational.org/conferences/snpd-2024/ |C |CORE2021 | -|International Conference on Model and Data Engineering |ML/CS |Workshops | |C |CORE2021 | -|IEEE International Symposium on Artificial Life |ML/CS, Specific | | |C |CORE2021 | -|International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems |ML/CS | | |C |CORE2021 | -|FRUCT |ML/CS |Posters |https://www.fruct.org/conferences/35/call-for-participation/|- |- | -|MMPR/IOI |ML/CS | | |- |- | -|AIST |CV, IR/Mining, ML/CS, NLP | |https://aistconf.org/ |- |- | -|L@S : ACM Conference on Learning @ Scale |ML/CS | |https://learningatscale.hosting.acm.org/las2024/ |- |- | -|International Work-Conference on Artificial and Natural Neural Networks |ML/CS | | |- |- | -|International Symposium on Artificial Intelligence and Mathematics |ML/CS | |https://isaim2024.cs.ou.edu/ |- |- | -|MIPT conference |ML/CS | |https://conf.mipt.ru/ |- |- | -|SGAI International Conference on Artificial Intelligence |ML/CS | | |- |- | -|International Conference on Hybrid Artificial Intelligence Systems |ML/CS | | |- |- | -|International Conference on Artificial Intelligence: Methodology, Systems, Applications |ML/CS | | |- |- | -|IEEE International Conference on Data Science and Engineering |ML/CS | | |- |- | -|Portuguese Conference on Artificial Intelligence |ML/CS |StudentThesis / Doctor symposium | |- |- | -|Lomonosov |ML/CS | |https://lomonosov-msu.ru/eng/event/9000/ |- |- | -|International Conference on Machine Learning and Cybernetics |ML/CS | |https://www.icmlc.com/ |- |- | -|Conference on Visualization and Data Analysis |CV, ML/CS | | |- |- | -|AutoML |ML/CS |Tutorials, Workshops |https://2024.automl.cc/ |- |- | -|International Conference on Distributed Computing and Artificial Intelligence |ML/CS | | |- |- | -|Florida Artificial Intelligence Research Society Conference |ML/CS | |https://www.flairs-37.info/ |- |- | -|International Work-conference on the Interplay between Natural and Artificial Computation |ML/CS | | |- |- | -|International Conference on Artificial Intelligence |ML/CS | | |- |- | -|GECCO: Genetic and Evolutionary Computation Conference |ML/CS, Specific | |https://gecco-2024.sigevo.org/HomePage |- |- | -|Language, Data and Knowledge |IR/Mining, ML/CS, NLP |Posters, Tutorials, Workshops | |- |- | -|Asian Conference on Machine Learning |ML/CS |Workshops | |- |- | -|AIES : AAAI/ACM Conference on AI, Ethics, and Society |ML/CS, Specific | | |- |- | -|International Conference on Artificial Intelligence and Soft Computing |ML/CS | |https://icaisc.eu/ |- |- | +| Conference name | Category | Conference program | URL | Rank | Rank system | +| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------- | ----------------------------------------------------------------------------------- | ------------------------------------------------------------ | ---- | ----------- | +| SIGBOVIK | Specific | | http://sigbovik.org/ | - | - | +| ECIR : European Conference on Information Retrieval | IR/Mining | Demo, Industrial, Tutorials, Workshops | https://www.ecir2024.org/ | A | CORE2021 | +| SIGIR: International ACM SIGIR Conference on Research and Development in Information Retrieval | IR/Mining | | https://sigir-2024.github.io/ | A | CORE2021 | +| WWW: International World Wide Web Conferences | IR/Mining | Demo, StudentThesis / Doctor symposium, Tutorials, Workshops | https://www2024.thewebconf.org/ | A | CORE2021 | +| ESWC : Extended Semantic Web Conference | IR/Mining | | https://2024.eswc-conferences.org/ | A | CORE2021 | +| MSR : Mining Software Repositories | IR/Mining, Specific | | https://2024.msrconf.org/ | A | CORE2021 | +| WSDM : ACM International Conference on Web Search and Data Mining | IR/Mining | | https://www.wsdm-conference.org/2024/ | A | CORE2021 | +| PODS : ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems | IR/Mining | Demo, Industrial, Tutorials, Workshops | https://2024.sigmod.org/ | A | CORE2021 | +| RecSys : ACM Conference on Recommender Systems | IR/Mining | Tutorials, Workshops | https://recsys.acm.org/recsys24/ | A | CORE2021 | +| EDBT : International Conference on Extending Database Technology | IR/Mining | StudentThesis / Doctor symposium, Workshops | https://edbt.org/ | A | CORE2021 | +| DASFAA : International Conference on Database Systems for Advanced Applications | IR/Mining | | https://www.dasfaa2024.org/ | B | CORE2021 | +| SSBSE : International Conference on Search based Software Engineering | IR/Mining | | https://ssbse.info/ | B | CORE2021 | +| UMAP : International Conference on User Modelling, Adaptation, and Personalization | IR/Mining, Specific | | https://www.um.org/umap2024/ | B | CORE2021 | +| Pacific Asia Conference on Language, Information and Computation | IR/Mining | | | B | CORE2021 | +| International Conference on Formal Ontology in Information Systems | IR/Mining, Specific | | | B | CORE2021 | +| ADBIS : Advances in Databases and Information Systems | IR/Mining | StudentThesis / Doctor symposium, Tutorials, Workshops | https://conferences.sigappfr.org/adbis2024/ | B | CORE2021 | +| WISE : International Conference on Web Information Systems Engineering | IR/Mining | | https://wise2024-qatar.com/ | B | CORE2021 | +| Workshop on Logic, Language, Information and Computation | IR/Mining, NLP | | https://wollic2024.inf.unibe.ch/ | B | CORE2021 | +| EKAW : Knowledge Engineering and Knowledge Management | IR/Mining | | | B | CORE2021 | +| TPDL : International Conference on Theory and Practice of Digital Libraries | IR/Mining | | | B | CORE2021 | +| International Conference on Knowledge-Based and Intelligent Information and Engineering Systems | IR/Mining | Workshops | http://kes2024.kesinternational.org/ | B | CORE2021 | +| Asian Conference on Intelligent Information and Database Systems | IR/Mining | | https://aciids.pwr.edu.pl/2024/ | B | CORE2021 | +| ADMA : International Conference on Advanced Data Mining and Applications | IR/Mining | | https://adma2024.github.io/ | B | CORE2021 | +| WI : IEEE/WIC/ACM International Conference on Web Intelligence | IR/Mining | SpecialSession, Workshops | | B | CORE2021 | +| International Symposium on Computer and Information Sciences | IR/Mining | | https://www.iscsic.org/ | C | CORE2021 | +| European-Japanese Conference on Information Modelling and Knowledge Bases | IR/Mining | | https://ejc2024.ds.musashino-u.ac.jp/ | C | CORE2021 | +| International Conference on Information Technology and Applications | IR/Mining | SpecialSession, Workshops | https://www.icita.world/#/ | C | CORE2021 | +| International Conference on Legal Knowledge and Information Systems | IR/Mining, Specific | | | C | CORE2021 | +| Asia Information Retrieval Symposium | IR/Mining | | | C | CORE2021 | +| TREC | IR/Mining, NLP | | | - | - | +| ASONAM : International Conference on Advances in Social Network Analysis and Mining | IR/Mining | | | - | - | +| IEEE International Conference on Information and Automation | IR/Mining, ML/CS, Specific | | | - | - | +| WebSci : ACM on Web Science Conference | IR/Mining | Tutorials, Workshops | https://websci24.org/ | - | - | +| ISWC : International Semantic Web Conference | IR/Mining | Tutorials, Workshops | | - | - | +| BTAS : IEEE International Conference on Biometrics: Theory Applications and Systems (BTAS) | IR/Mining, Specific | | | - | - | +| Russir | IR/Mining, NLP | | | - | - | +| Statistical and Scientific Database Management | IR/Mining | | https://ssdbm.org/2024/ | - | - | +| International Conference on Information and Knowledge Engineering | IR/Mining, Specific | | | - | - | +| International Conference on the Theory of Information Retrieval | IR/Mining | | | - | - | +| IJCB : International Joint Conference on Biometrics | IR/Mining, Specific | Demo, StudentThesis / Doctor symposium, Tutorials | | - | - | +| CHIIR : Conference on Human Information Interaction and Retrieval | IR/Mining | | https://chiir2024.github.io/ | - | - | +| Conference on Information Sciences and Systems | IR/Mining | | https://ee-ciss.princeton.edu/ | - | - | +| International Baltic Conference on Databases and Information Systems | IR/Mining | | | - | - | +| ICWSM : International Conference on Web and Social Media | IR/Mining | | https://www.icwsm.org/2024/index.html/ | - | - | +| BigMM : IEEE International Conference on Multimedia Big Data | IR/Mining | | | - | - | +| SemEval : International Workshop on Semantic Evaluation | CV, IR/Mining, NLP, Signal | | https://semeval.github.io/SemEval2024/ | - | - | +| AVSS : IEEE International Conference on Advanced Video and Signal-Based Surveillance | Signal | | https://zinc.cse.buffalo.edu/ubmdfl/AVSS2024/index.php | B | CORE2021 | +| MMSP : IEEE Workshop on Multimedia Signal Processing | Signal | Demo, SpecialSession | | B | CORE2021 | +| International Conference on Image and Signal Processing | Signal | | https://csita2024.org/ispr/index | C | CORE2021 | +| IEEE Symposium on Computational intelligence for Multimedia Signal and Vision Processing | Signal | | | C | CORE2021 | +| DCASE : Detection and Classification of Acoustic Scenes and Events | Signal | Contests, Workshops | | - | - | +| ISMIR : International Society for Music Information Retrieval Conference | IR/Mining, Signal, Specific | Tutorials | https://ismir2024.ismir.net/ | - | - | +| EUSIPCO : European Signal Processing Conference | Signal | Tutorials, Workshops | https://eusipcolyon.sciencesconf.org/ | - | - | +| International Conference on Robotics, Vision, Signal Processing and Power Applications (was ROVPIA) | Signal, Specific | | | - | - | +| ICASSP: International Conference on Acoustics, Speech and Signal Processing | Signal | | https://2024.ieeeicassp.org/ | - | - | +| SLT : IEEE Spoken Language Technology Workshop | Signal | Contests, Demo, Hackaton, Workshops | | - | - | +| ACM Symposium on Eye Tracking Research and Applications | CV, Signal, Specific | | https://etra.acm.org/2024/ | - | - | +| International Conference on Advanced Technologies For Signal & Image Processing | Signal | | | - | - | +| WASPAA : IEEE Workshop on Applications of Signal Processing to Audio and Acoustics | Signal | | | - | - | +| SPAWC | Signal | | https://spawc2024.org/ | - | - | +| APSIPA : Asia-Pacific Signal and Information Processing Association Annual Summit and Conference | Signal | | | - | - | +| SSP : IEEE Statistical Signal Processing Workshop | Signal | | | - | - | +| INTERSPEECH: Conference of the International Speech Communication Association | Signal | | https://interspeech2024.org/ | - | - | +| MIPR : IEEE Conference on Multimedia Information Processing and Retrieval | IR/Mining, Signal | Tutorials, Workshops | | - | - | +| ACSSC : Asilomar Conference on Signals, Systems and Computers | ML/CS, Signal | | | - | - | +| WCSP : International Conference on Wireless Communications and Signal Processing | Signal | | | - | - | +| SAM : IEEE Sensor Array and Multichannel Signal Processing Workshop | Signal | | https://2024.ieeesam.org/ | - | - | +| ICME: International Conference on Multimedia and Expo | CV, NLP, Signal | | https://2024.ieeeicme.org/ | A | CORE2021 | +| EACL : Conference of the European Chapter of the Association for Computational Linguistics | NLP | | https://2024.eacl.org/ | A | CORE2021 | +| CoNLL: Conference on Computational Natural Language Learning | NLP | | | A | CORE2021 | +| ACL: Annual Meeting of the Association for Computational Linguistics | NLP | | https://2024.aclweb.org/ | A | CORE2021 | +| EMNLP: Conference on Empirical Methods in Natural Language Processing | NLP | TBA | | A | CORE2021 | +| COLING: International Conference on Computational Linguistics | NLP | Tutorials, Workshops | https://lrec-coling-2024.org/ | A | CORE2021 | +| NAACL: North American Chapter of the Association for Computational Linguistics | NLP | Demo, Industrial, Workshops | https://2024.naacl.org/ | A | CORE2021 | +| SIGDIAL : Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL) | NLP | SpecialSession | https://2024.sigdial.org/ | B | CORE2021 | +| IJCNLP : International Joint Conference on Natural Language Processing (IJCNLP) | NLP | Tutorials, Workshops | | B | - | +| DAS : IAPR International Workshop on Document Analysis Systems | NLP | SpecialSession | | B | CORE2021 | +| NLDB : International Conference on Applications of Natural Language to Information Systems | NLP | | https://nldb2024.di.unito.it/ | C | CORE2021 | +| LREC : International Conference on Language Resources and Evaluation (LREC) | NLP, Signal | | https://lrec-coling-2024.org/ | C | CORE2021 | +| Dialogue | NLP | Contests | http://www.dialog-21.ru/ | - | - | +| CLEF : International Conference of the Cross-Language Evaluation Forum for European Languages | CV, IR/Mining, NLP, Signal | | https://clef2024.clef-initiative.eu/ | - | - | +| SEM : Joint Conference on Lexical and Computational Semantics | NLP | | https://sites.google.com/view/starsem2024 | - | - | +| International Conference on Recent Advances in Natural Language Processing | NLP | Tutorials, Workshops | | - | - | +| AINL | NLP | | | - | - | +| IROS: International Conference on Intelligent Robots and Systems | CV | Tutorials, Workshops | | A | CORE2021 | +| ACMMM: ACM Multimedia | CV, NLP, Signal | Demo, StudentThesis / Doctor symposium, Workshops | | A | CORE2021 | +| ICCV: International Conference on Computer Vision | CV | TBA | | A | CORE2021 | +| ECCV: European Conference on Computer Vision | CV | | https://eccv2024.ecva.net/ | A | CORE2021 | +| MICCAI : Medical Image Computing and Computer Assisted Intervention | CV, Specific | | http://www.miccai.org/ | A | CORE2021 | +| ICDAR : International Conference on Document Analysis and Recognition | CV, IR/Mining, NLP | | https://icdar2024.net/ | A | CORE2021 | +| WACV: Winter Conference on Applications of Computer Vision | CV | | https://wacv2024.thecvf.com/ | A | CORE2021 | +| CVPR: IEEE Conference on Computer Vision and Pattern Recognition | CV | Tutorials, Workshops | https://cvpr.thecvf.com/ | A | CORE2021 | +| ICMR: ACM International Conference on Multimedia Retrieval | CV, IR/Mining, NLP, Signal | | http://icmr2024.org/ | B | CORE2021 | +| Advanced Concepts for Intelligent Vision Systems | CV | | | B | CORE2021 | +| ICIP: International Conference on Image Processing | CV | Demo, SpecialSession, Tutorials, Workshops | https://2024.ieeeicip.org/ | B | CORE2021 | +| Image and Vision Computing Conference | CV | | | B | CORE2021 | +| ACCV: Asian Conference on Computer Vision | CV | Demo, StudentThesis / Doctor symposium, Tutorials, Workshops | https://accv2024.org/ | B | CORE2021 | +| FG : IEEE International Conference on Automatic Face & Gesture Recognition | CV | | https://fg2024.ieee-biometrics.org/ | C | CORE2021 | +| International Conference on Control, Automation, Robotics and Vision | CV, Specific | | | C | CORE2021 | +| International Conference on Computer Vision Systems | CV | Tutorials, Workshops | | C | CORE2021 | +| International Conference on Machine Vision | CV | SpecialSession | | C | CORE2021 | +| BMVC: British Machine Vision Conference | CV | Workshops | | - | - | +| MLMI : International Workshop on Machine Learning in Medical Imaging | CV | | | - | - | +| 3DV : International Conference on 3D Vision | CV | Demo, Tutorials | https://3dvconf.github.io/2024/ | - | - | +| ISBI : IEEE International Symposium on Biomedical Imaging | CV, Specific | SpecialSession, Tutorials | https://biomedicalimaging.org/2024/ | - | - | +| International Conference on Computer Vision and Graphics | CV | | | - | - | +| International Machine Vision and Image Processing Conference | CV | Workshops | | - | - | +| Machine Vision Applications | CV | | | - | - | +| International Conferences in Central Europe on Computer Graphics, Visualization and Computer Vision | CV | | | - | - | +| NeurIPS: Neural Information Processing Systems | ML/CS | BestPaperAward, Demo, Industrial, StudentPaper, Tutorials, Workshops | https://nips.cc/Conferences/2023 | A | CORE2021 | +| IJCAI: International Joint Conference on Artificial Intelligence | ML/CS | | https://ijcai24.org/ | A | CORE2021 | +| ECMLPKDD: European Conference on Machine learning and knowledge discovery in databases | IR/Mining, ML/CS | Tutorials, Workshops | https://2024.ecmlpkdd.org/ | A | CORE2021 | +| ICML: International Conference on Machine Learning | ML/CS | | https://icml.cc/Conferences/2024 | A | CORE2021 | +| PAKDD: Pacific-Asia Conference on Knowledge Discovery and Data Mining | IR/Mining, ML/CS | TBA | https://pakdd2024.org/ | A | CORE2021 | +| SIGKDD : ACM SIGKDD International Conference on Knowledge discovery and data mining | IR/Mining, ML/CS | | https://kdd.org/kdd2024/ | A | CORE2021 | +| LAK : International Conference on Learning Analytics And Knowledge | IR/Mining, ML/CS | StudentThesis / Doctor symposium | https://www.solaresearch.org/events/lak/lak24/ | A | CORE2021 | +| ICLR: International Conference on Learning Representations | ML/CS | TBA | https://iclr.cc/Conferences/2024 | A | CORE2021 | +| ICDE : International Conference on Data Engineering Workshops | ML/CS | | https://icde2024.github.io/ | A | CORE2021 | +| CIKM: ACM International Conference on Information and Knowledge Management | IR/Mining, ML/CS | | https://www.cikm2024.org/ | A | CORE2021 | +| European Conference on Artificial Intelligence | ML/CS | Tutorials, Workshops | https://www.ecai2024.eu/ | A | CORE2021 | +| IEEE International Conference on Data Science and Advanced Analytics | ML/CS | Tutorials | https://conferences.sigappfr.org/dsaa2023/ | A | CORE2021 | +| AISTATS: International Conference on Artificial Intelligence and Statistics | ML/CS | | https://aistats.org/aistats2024/ | A | CORE2021 | +| LICS : IEEE Symposium on Logic in Computer Science | ML/CS, Specific | | https://lics.siglog.org/lics24/ | A | CORE2021 | +| CIDR : Conference on Innovative Data Systems Research | ML/CS | | http://www.cidrdb.org/cidr2024/index.html | A | CORE2021 | +| SDM : SIAM International Conference on Data Mining (SDM) | ML/CS | | https://www.siam.org/conferences/cm/conference/sdm24 | A | CORE2021 | +| KR: International Conference on Principles of Knowledge Representation and Reasoning | IR/Mining, ML/CS | StudentThesis / Doctor symposium, Tutorials, Workshops | https://kr.org/KR2024/ | A | CORE2021 | +| SODA : ACM SIAM Symposium on Discrete Algorithms | ML/CS | | https://www.siam.org/conferences/cm/conference/soda24 | A | CORE2021 | +| ICDMW : IEEE International Conference on Data Mining | ML/CS | Tutorials, Workshops | https://www.cloud-conf.net/icdm2023/ | A | CORE2021 | +| UAI: Conference on Uncertainty in Artificial Intelligence | ML/CS | | https://www.auai.org/uai2024/ | A | CORE2021 | +| Logics in Artificial Intelligence, European Conference | ML/CS, Specific | | | A | CORE2021 | +| COLT: Conference on Learning Theory | ML/CS | | https://learningtheory.org/colt2024/ | A | CORE2021 | +| SIGMOD : ACM SIGMOD International Conference on Management of Data | ML/CS | TBA | https://2024.sigmod.org/ | A | CORE2021 | +| STOC : ACM Symposium on Theory of Computing | ML/CS, Specific | | http://acm-stoc.org/stoc2024/ | A | CORE2021 | +| AAAI: Association for the Advancement of Artificial Intelligence | ML/CS | | https://aaai.org/aaai-conference/ | A | CORE2021 | +| International Conference on Artificial Intelligence in Education | ML/CS, Specific | | https://www.aied2023.org/ | A | CORE2021 | +| ICPR : International Conference on Pattern Recognition | ML/CS | | http://www.icprs.org/ | B | CORE2021 | +| FUZZ : IEEE International Conference on Fuzzy Systems | ML/CS | | | B | CORE2021 | +| International Conference on Tools with Artificial Intelligence | ML/CS | | | B | CORE2021 | +| Australasian Joint Conference on Artificial Intelligence | ML/CS | Tutorials, Workshops | | B | CORE2021 | +| Educational Data Mining | IR/Mining, ML/CS, Specific | | https://educationaldatamining.org/edm2024/ | B | CORE2021 | +| International Conference on Integration of Artificial Intelligence and Operations Research Techniques in Constraint Programming for Combinatorial Optimization Problems | ML/CS | | https://sites.google.com/view/cpaior2024 | B | CORE2021 | +| Big Data : IEEE International Conference on Big Data | IR/Mining, ML/CS | SpecialSession, Tutorials, Workshops | https://bigdataieee.org/BigData2024/ | B | CORE2021 | +| DCC : Data Compression Conference | ML/CS, Specific | | https://www.cs.brandeis.edu/~dcc/index.html | B | CORE2021 | +| International Conference on Scientific and Statistical Data Base Management | ML/CS | | https://ssdbm.org/2024/ | B | CORE2021 | +| Web and Big Data | IR/Mining, ML/CS | Workshops | | B | CORE2021 | +| Pacific Rim International Conference on Artificial Intelligence | ML/CS | Tutorials, Workshops | | B | CORE2021 | +| IFIP WG 11.3 Working Conference on Data and Applications Security (also known as DBSEC) | ML/CS, Specific | | | B | CORE2021 | +| Australian Data Mining Conference | IR/Mining, ML/CS | StudentThesis / Doctor symposium, Tutorials, Workshops | | B | CORE2021 | +| SAC : ACM Symposium on Applied Computing | ML/CS | | http://www.sigapp.org/sac/sac2024/ | B | CORE2021 | +| International Conference on Agents and Artificial Intelligence | ML/CS | Demo, Panel, SpecialSession, StudentThesis / Doctor symposium, Tutorials, Workshops | https://icaart.scitevents.org/ | B | CORE2021 | +| Artificial Intelligence in Medicine in Europe | ML/CS, Specific | | https://www.aimedicine.info/aime24/ | B | CORE2021 | +| European Symposium on Artificial Neural Networks | ML/CS | | https://www.esann.org/ | B | CORE2021 | +| SMC : IEEE International Conference on Systems, Man and Cybernetics | ML/CS | Tutorials, Workshops | https://ieeesmc2024.org/ | B | CORE2021 | +| International Conference on Modelling Decisions for Artificial Intelligence | ML/CS | | http://www.mdai.cat/mdai2024/ | B | CORE2021 | +| International Conference on Neural Information Processing | ML/CS | Tutorials, Workshops | | B | CORE2021 | +| Intelligent Data Analysis | ML/CS | | https://ida2024.org/ | B | CORE2021 | +| IV : IEEE Intelligent Vehicles Symposium | ML/CS, Specific | | https://2024.ieee-iv.org/ | B | CORE2021 | +| IJCNN: International Joint Conference on Neural Networks | ML/CS | | | B | CORE2021 | +| Data Warehousing and Knowledge Discovery | IR/Mining, ML/CS | Workshops | https://www.dexa.org/dawak2024 | B | CORE2021 | +| CEC : IEEE Congress on Evolutionary Computation | ML/CS, Specific | | | B | CORE2021 | +| ISIT : IEEE International Symposium on Information Theory | ML/CS | | https://2024.ieee-isit.org/home | B | CORE2021 | +| International Conference on Intelligent Data Engineering and Automated Learning | ML/CS, Specific | SpecialSession | https://ideal2023.uevora.pt/ | C | CORE2021 | +| EURO | ML/CS | | https://euro2024cph.dk/ | C | CORE2021 | +| Artificial Intelligence Applications and Innovations | ML/CS | | https://ifipaiai.org/ | C | CORE2021 | +| International Symposium on Artificial Life and Robotics | ML/CS | | https://isarob.org/symposium/ | C | CORE2021 | +| International FLINS Conference on Robotics and Artificial Intelligence (was International Fuzzy Logic and Intelligent technologies in Nuclear Science Conference) | ML/CS | | | C | CORE2021 | +| International Conference on Engineering Applications of Neural Networks | ML/CS | | https://eannconf.org/2024/ | C | CORE2021 | +| IEEE/ACM International Conference on Big Data Computing, Applications and Technologies | ML/CS | Workshops | https://bdcat-conference.org/ | C | CORE2021 | +| IEEE Symposium on Computational Intelligence and Data Mining | ML/CS | Workshops | | C | CORE2021 | +| International Conference on Internet of Things, Big Data and Security | ML/CS | Demo, Panel, SpecialSession, Tutorials, Workshops | https://iotbds.scitevents.org/ | C | CORE2021 | +| International Symposium on Neural Networks | ML/CS | | https://conference.cs.cityu.edu.hk/isnn/ | C | CORE2021 | +| FUSION : International Conference on Information Fusion | ML/CS | | | C | CORE2021 | +| International Conference on Machine Learning and Applications | ML/CS | SpecialSession | https://www.icmla-conference.org/icmla24/ | C | CORE2021 | +| International Cross-Domain Conference for Machine Learning and Knowledge Extraction | IR/Mining, ML/CS, NLP | SpecialSession | | C | CORE2021 | +| ICANN: International Conference on Artificial Neural Networks | ML/CS | | https://e-nns.org/icann2024/ | C | CORE2021 | +| International Conference on Artificial Intelligence and Law | ML/CS, Specific | | | C | CORE2021 | +| International Conference on Data Science, Technology and Applications | ML/CS | TBA | https://data.scitevents.org/ | C | CORE2021 | +| International Conference on the Statistical Analysis of Textual Data | ML/CS, NLP | | | C | CORE2021 | +| International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing | ML/CS | SpecialSession, Workshops | https://acisinternational.org/conferences/snpd-2024/ | C | CORE2021 | +| International Conference on Model and Data Engineering | ML/CS | Workshops | | C | CORE2021 | +| IEEE International Symposium on Artificial Life | ML/CS, Specific | | | C | CORE2021 | +| International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems | ML/CS | | | C | CORE2021 | +| FRUCT | ML/CS | Posters | https://www.fruct.org/conferences/35/call-for-participation/ | - | - | +| MMPR/IOI | ML/CS | | | - | - | +| AIST | CV, IR/Mining, ML/CS, NLP | | https://aistconf.org/ | - | - | +| L@S : ACM Conference on Learning @ Scale | ML/CS | | https://learningatscale.hosting.acm.org/las2024/ | - | - | +| International Work-Conference on Artificial and Natural Neural Networks | ML/CS | | | - | - | +| International Symposium on Artificial Intelligence and Mathematics | ML/CS | | https://isaim2024.cs.ou.edu/ | - | - | +| MIPT conference | ML/CS | | https://conf.mipt.ru/ | - | - | +| SGAI International Conference on Artificial Intelligence | ML/CS | | | - | - | +| International Conference on Hybrid Artificial Intelligence Systems | ML/CS | | | - | - | +| International Conference on Artificial Intelligence: Methodology, Systems, Applications | ML/CS | | | - | - | +| IEEE International Conference on Data Science and Engineering | ML/CS | | | - | - | +| Portuguese Conference on Artificial Intelligence | ML/CS | StudentThesis / Doctor symposium | | - | - | +| Lomonosov | ML/CS | | https://lomonosov-msu.ru/eng/event/9000/ | - | - | +| International Conference on Machine Learning and Cybernetics | ML/CS | | https://www.icmlc.com/ | - | - | +| Conference on Visualization and Data Analysis | CV, ML/CS | | | - | - | +| AutoML | ML/CS | Tutorials, Workshops | https://2024.automl.cc/ | - | - | +| International Conference on Distributed Computing and Artificial Intelligence | ML/CS | | | - | - | +| Florida Artificial Intelligence Research Society Conference | ML/CS | | https://www.flairs-37.info/ | - | - | +| International Work-conference on the Interplay between Natural and Artificial Computation | ML/CS | | | - | - | +| International Conference on Artificial Intelligence | ML/CS | | | - | - | +| GECCO: Genetic and Evolutionary Computation Conference | ML/CS, Specific | | https://gecco-2024.sigevo.org/HomePage | - | - | +| Language, Data and Knowledge | IR/Mining, ML/CS, NLP | Posters, Tutorials, Workshops | | - | - | +| Asian Conference on Machine Learning | ML/CS | Workshops | | - | - | +| AIES : AAAI/ACM Conference on AI, Ethics, and Society | ML/CS, Specific | | | - | - | +| International Conference on Artificial Intelligence and Soft Computing | ML/CS | | https://icaisc.eu/ | - | - | -## Journals +### Journals -|Journal name |Category |Impact|URL | -|--------------------------------------------------------------------------------------------------------------|------------------------|------|-------------------------------------------------------------------------------------------------------------| -|Foundations and Trends in Machine Learning |ML |38.78 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34 | -|International Journal of Information Management |ML |21.35 |https://robotics.sciencemag.org/ | -|Science Robotics |ML, Specific |17.02 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=9670 | -|IEEE Transactions on Pattern Analysis and Machine Intelligence |CV, Comp. Math, ML |15.84 |https://www.journals.elsevier.com/signal-processing | -|Nature Machine Intelligence |ML |13.63 |https://www.frontiersin.org/journals/robotics-and-ai | -|Artificial Intelligence Review |ML, NLP |11.67 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6570654 | -|IEEE Transactions on Neural Networks and Learning Systems |ML |10.47 |https://www.osapublishing.org/josaa/home.cfm | -|IEEE Transactions on Fuzzy Systems |Comp. Math, ML |10.12 |https://www.springer.com/journal/521 | -|ACM Transactions on Intelligent Systems and Technology |ML |9.9 |https://www.springer.com/journal/11721 | -|Neural Networks |ML |9.7 |https://www.journals.elsevier.com/neurocomputing | -|Expert Systems with Applications |ML |9.6 |https://www.springer.com/journal/12559 | -|International Journal of Intelligent Systems |ML |9.34 |https://www.comsoc.org/publications/journals/ieee-tccn | -|Soft Robotics |ML, Specific |9.22 |http://www.jmlr.org/ | -|Journal of Intelligent Manufacturing |ML |9.18 |https://www.journals.elsevier.com/international-journal-of-information-management/ | -|CAAI Transactions on Intelligence Technology |ML |9.11 |??? | -|Knowledge-Based Systems |ML |8.66 |https://www.sciencedirect.com/journal/pattern-recognition | -|Engineering Applications of Artificial Intelligence |ML |8.64 |https://www.journals.elsevier.com/digital-signal-processing | -|Pattern Recognition |CV, ML, NLP, Signal |8.54 |https://www.springer.com/journal/11548 | -|Advanced Engineering Informatics |ML |8.53 |https://link.springer.com/journal/10845 | -|Information Sciences |ML |8.51 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6221037 | -|Artificial Intelligence in Medicine |ML, Specific |8.3 |https://www.journals.elsevier.com/neural-networks | -|IEEE/CAA Journal of Automatica Sinica |ML |7.7 |https://onlinelibrary.wiley.com/journal/14680394 | -|International Journal of Robotics Research |ML, Specific |7.38 |https://onlinelibrary.wiley.com/journal/1098111x | -|IEEE Transactions on Cognitive Communications and Networking |ML |7.12 |https://www.journals.elsevier.com/fuzzy-sets-and-systems | -|Neurocomputing |ML |6.19 |https://www.springer.com/journal/10115 | -|Fuzzy Optimization and Decision Making |ML |6.06 |http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=91 | -|Cognitive Systems Research |ML |5.99 |https://www.springer.com/journal/10951 | -|Minds and Machines |ML |5.92 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7274989 | -|IEEE Intelligent Systems |ML |5.82 |http://www.elsevier.com/wps/find/journaldescription.cws_home/505651/description#description | -|IEEE Computational Intelligence Magazine |ML |5.71 |https://www.mdpi.com/journal/jimaging | -|Pattern Recognition Letters |CV, ML, NLP, Signal |5.67 |https://www.springer.com/journal/10700 | -|Computational Linguistics |ML, NLP |5.63 |http://journals.cambridge.org/action/displayJournal?jid=NLE | -|Neural Computing and Applications |ML |5.6 |https://www.journals.elsevier.com/journal-of-memory-and-language | -|Artificial Intelligence |ML, NLP |5.57 |https://www.sciencedirect.com/journal/medical-image-analysis | -|Applied Intelligence |ML |5.44 |https://www.journals.elsevier.com/knowledge-based-systems | -|Integrated Computer-Aided Engineering |Comp. Math, ML |5.44 |http://online.liebertpub.com/soro | -|Journal of Machine Learning Research |ML |5.41 |https://journals.sagepub.com/home/ijr | -|Journal of Parallel and Distributed Computing |ML, Specific |5.27 |https://www.tandfonline.com/toc/teta20/current | -|Progress in Artificial Intelligence |ML |5.2 |https://www.springer.com/journal/10339 | -|Artificial Intelligence and Law |ML, Specific |4.94 |https://www.springer.com/journal/10851 | -|Fuzzy Sets and Systems |ML |4.76 |https://www.journals.elsevier.com/artificial-intelligence/ | -|ACM Transactions on Human-Robot Interaction |ML |4.69 |??? | -|International Journal of Machine Learning and Cybernetics |CV, ML |4.66 |https://www.iospress.nl/journal/integrated-computer-aided-engineering/ | -|Journal of Artificial Intelligence and Soft Computing Research |CV, ML |4.62 |https://www.tandfonline.com/toc/hscc20/current | -|IEEE Transactions on Human-Machine Systems |ML, Signal |4.6 |https://www.journals.elsevier.com/engineering-applications-of-artificial-intelligence | -|Machine Learning |ML |4.54 |https://dl.acm.org/journal/tcps | -|Design Studies |ML, Specific |4.36 |https://www.springer.com/journal/41315 | -|International Journal of Approximate Reasoning |ML, Specific |4.31 |https://www.hindawi.com/journals/acisc/ | -|International Journal of Fuzzy Systems |Comp. Math, ML |4.23 |https://www.journals.elsevier.com/advanced-engineering-informatics | -|Frontiers in Neurorobotics |ML, Specific |4.08 |http://www.springer.com/computer+science/ai/journal/10489 | -|Applied Computational Intelligence and Soft Computing |ML |4.07 |https://journals.sagepub.com/home/arx | -|Network Neuroscience |ML |4.07 |https://www.springer.com/journal/11067 | -|Autonomous Robots |ML, Specific |3.94 |https://www.springer.com/journal/10032 | -|Big Data and Cognitive Computing |ML |3.9 |https://www.springer.com/journal/498 | -|Journal of Intelligent and Robotic Systems: Theory and Applications |ML, Specific |3.61 |https://www.springer.com/journal/10601 | -|Journal of Artificial Intelligence Research |ML |3.59 |https://www.journals.elsevier.com/expert-systems-with-applications | -|Frontiers in Robotics and AI |ML |3.47 |??? | -|IEEE Transactions on Cognitive and Developmental Systems |ML |3.45 |https://onlinelibrary.wiley.com/journal/17568765 | -|Robotics |ML, Specific |3.4 |https://dl.acm.org/journal/jacm | -|Autonomous Agents and Multi-Agent Systems |ML |3.38 |??? | -|Swarm Intelligence |ML, Specific |3.31 |https://www.journals.elsevier.com/information-sciences | -|Intelligent Service Robotics |ML, Specific |3.15 |https://www.mitpressjournals.org/netn | -|Digital Signal Processing: A Review Journal |Comp. Math, ML, Signal |3.15 |http://jaiscr.eu/ | -|Expert Systems |Comp. Math, ML |3.09 |https://www.jair.org/index.php/jair | -|ACM Transactions on Cyber-Physical Systems |ML |3.08 |http://www.springer.com/computer+science/ai/journal/11063 | -|Knowledge and Information Systems |ML |3.06 |https://link.springer.com/journal/11263 | -|Computational Intelligence |Comp. Math, ML |3.02 |https://www.springer.com/journal/10458 | -|Evolutionary Intelligence |ML |2.96 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5962385 | -|Journal of Intelligent Information Systems |ML |2.94 |https://www.mitpressjournals.org/loi/coli | -|Applied Artificial Intelligence |ML |2.92 |http://www.computability.de/journal/ | -|AI and Society |ML |2.87 |https://www.iospress.nl/journal/argument-computation/ | -|Journal of the ACM |ML |2.87 |https://www.journals.elsevier.com/design-studies | -|AI Magazine |ML |2.87 |https://www.springer.com/journal/10844 | -|Journal of Experimental and Theoretical Artificial Intelligence |ML |2.85 |https://www.springer.com/journal/10732 | -|Systems Science and Control Engineering |ML |2.8 |http://www.actapress.com/Content_of_Journal.aspx?JournalID=119 | -|Neural Processing Letters |ML |2.8 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4200690 | -|Topics in Cognitive Science |ML |2.74 |https://www.cambridge.org/core/journals/theory-and-practice-of-logic-programming | -|Applied System Innovation |ML, Specific |2.73 |https://www.journals.elsevier.com/physics-of-life-reviews | -|IET Cyber-Physical Systems: Theory and Applications |ML |2.72 |https://www.springer.com/journal/10590 | -|ACM Transactions on Interactive Intelligent Systems |ML |2.47 |https://www.springer.com/journal/11023 | -|Networks and Spatial Economics |ML, Specific |2.4 |https://www.springer.com/journal/10846 | -|Knowledge Engineering Review |ML |2.39 |https://www.springer.com/journal/11370 | -|Physics of Life Reviews |Comp. Math, ML, Specific|2.38 |https://www.nowpublishers.com/MAL | -|Kybernetes |ML |2.38 |http://ijfs.usb.ac.ir/ | -|Cognitive Science |ML |2.35 |https://www.emerald.com/insight/publication/issn/0368-492X | -|Argument and Computation |Comp. Math, ML |2.28 |https://www.iospress.nl/journal/international-journal-of-knowledge-based-and-intelligent-engineering-systems/| -|Cybernetics and Systems |ML |2.24 |https://www.mdpi.com/journal/robotics | -|Iranian Journal of Fuzzy Systems |ML, Specific |2.24 |https://www.sciencedirect.com/journal/journal-of-parallel-and-distributed-computing | -|Journal of Heuristics |ML |2.24 |https://www.springer.com/journal/10994 | -|Journal of Scheduling |ML |2.2 |http://journals.cambridge.org/action/displayJournal?jid=KER | -|IEEE Transactions on Games |ML, Specific |2.18 |https://onlinelibrary.wiley.com/journal/14678640 | -|Journal of Intelligent Systems |ML |2.16 |https://www.springer.com/journal/146 | -|International Journal of Advanced Robotic Systems |ML |2.15 |https://www.springer.com/journal/10817 | -|Machine Translation |ML, NLP |2.15 |??? | -|Journal of Pragmatics |ML |2.11 |https://www.tandfonline.com/toc/uaai20/current | -|Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM |ML |2.04 |http://www.ijfis.org/main.html | -|Natural Language Engineering |ML, NLP |2.03 |https://onlinelibrary.wiley.com/journal/15516709 | -|Spatial Information Research |ML |2 |??? | -|Journal of Intelligent and Fuzzy Systems |ML, Specific |1.95 |https://www.tandfonline.com/toc/ucbs20/current | -|KI - Kunstliche Intelligenz |ML |1.91 |https://www.degruyter.com/view/journals/jisys/jisys-overview.xml | -|International Journal of Swarm Intelligence Research |ML |1.86 |https://academic.oup.com/jos | -|International Journal of Intelligent Robotics and Applications |ML |1.81 |https://dl.acm.org/journal/tiis | -|Theory and Practice of Logic Programming |Comp. Math, ML |1.73 |https://aaai.org/Magazine/magazine.php | -|International Journal of Knowledge and Systems Science |ML |1.69 |https://www.tandfonline.com/loi/lnfa20 | -|Journal on Data Semantics |CV, ML, NLP, Signal |1.68 |http://www.nnw.cz/ | -|International Journal of Pattern Recognition and Artificial Intelligence |CV, ML |1.67 |https://www.worldscientific.com/worldscinet/ijait | -|Journal of Automated Reasoning |Comp. Math, ML, Specific|1.66 |https://www.journals.elsevier.com/cognitive-systems-research | -|Bulletin of the Polish Academy of Sciences: Technical Sciences |ML |1.66 |https://www.journals.elsevier.com/journal-of-pragmatics | -|International Journal of Humanoid Robotics |ML, Specific |1.6 |https://www.worldscientific.com/worldscinet/ijprai | -|Neural Network World |ML |1.57 |https://www.fujipress.jp/jaciii/jc/ | -|Cognitive Processing |ML |1.45 |https://www.worldscientific.com/worldscinet/ijufks | -|Adaptive Behavior |ML |1.44 |https://www.worldscientific.com/worldscinet/ijhr | -|AI Communications |ML |1.37 |http://journals.pan.pl/dlibra/journal/119067 | -|International Journal of Software Innovation |ML |1.34 |https://journal.iberamia.org/index.php/intartif/index | -|International Journal on Artificial Intelligence Tools |ML |1.33 |https://www.worldscientific.com/worldscinet/ijseke | -|International Journal of Fuzzy Logic and Intelligent Systems |ML |1.31 |http://www.springer.com/computer+science/ai/journal/10472 | -|International Journal of Software Engineering and Knowledge Engineering |ML |1.31 |https://www.aicommunications.eu/ | -|Intelligent Data Analysis |CV, ML |1.3 |https://www.tandfonline.com/loi/tfie20 | -|Annals of Mathematics and Artificial Intelligence |Comp. Math, ML |1.3 |https://journals.sagepub.com/home/adb | -|International Journal of Robotics and Automation |ML, Specific |1.25 |https://www.iospress.nl/journal/intelligent-data-analysis/ | -|Informatica (Slovenia) |ML |1.21 |https://www.worldscientific.com/worldscinet/ijsc | -|International Journal of Cognitive Informatics and Natural Intelligence |ML |1.19 |??? | -|Parallel Computing |ML |1.16 |??? | -|International Journal of Uncertainty, Fuzziness and Knowlege-Based Systems |ML |1.15 |https://www.journals.elsevier.com/parallel-computing | -|Intelligenza Artificiale |ML |1.13 |https://www.kybernetika.cz/ | -|Journal of Semantics |ML |1.12 |https://constructivist.info/ | -|Inteligencia Artificial |ML |0.95 |https://www.igi-global.com/journal/international-journal-swarm-intelligence-research/1149 | -|Web Intelligence |ML |0.95 |https://www.springer.com/journal/10015 | -|Automatic Control and Computer Sciences |Comp. Math, ML |0.93 |https://digital-library.theiet.org/content/journals/iet-spr | -|Constraints |Comp. Math, ML |0.88 |https://www.iospress.nl/journal/journal-of-intelligent-fuzzy-systems/ | -|IEICE Transactions on Information and Systems |ML |0.88 |https://journals.agh.edu.pl/csci | -|International Journal of Semantic Computing |ML |0.84 |https://www.jstage.jst.go.jp/browse/transinf | -|Artificial Life and Robotics |ML |0.84 |https://www.iospress.nl/journal/intelligenza-artificiale/ | -|Computer Science |ML |0.83 |https://www.iospress.nl/journal/web-intelligence-and-agent-systems/ | -|International Journal of Knowledge-Based and Intelligent Engineering Systems |ML |0.81 |http://journals.cambridge.org/action/displayJournal?jid=AIE | -|Kybernetika |ML |0.8 |http://cogsci.snu.ac.kr/jcs/ | -|Computability |Comp. Math, ML |0.71 |https://www.springer.com/computer/database+management+%26+information+retrieval/journal/13740 | -|Journal of Advanced Computational Intelligence and Intelligent Informatics |ML |0.53 |https://www.igi-global.com/journal/international-journal-software-innovation/64245 | -|Journal of Robotics, Networking and Artificial Life |ML |0.49 |??? | -|Fuzzy Information and Engineering |ML |0.45 |http://www.informatica.si/index.php/informatica | -|Computer Science Journal of Moldova |ML |0.43 |https://www.igi-global.com/journal/international-journal-knowledge-systems-science/1169 | -|Journal of Cognitive Science |ML |0.39 |https://www.igi-global.com/journal/international-journal-cognitive-informatics-natural/1095 | -|Constructivist Foundations |ML |0.36 |https://www.tandfonline.com/action/journalInformation?journalCode=tssc20 | -|Medical Image Analysis |CV, Specific |15.24 |https://www.journals.elsevier.com/journal-of-visual-communication-and-image-representation | -|International Journal of Computer Vision |CV, ML |11.81 |https://www.journals.elsevier.com/pattern-recognition-letters | -|Computerized Medical Imaging and Graphics |CV |8.4 |https://www.springer.com/journal/12065 | -|IEEE Transactions on Visualization and Computer Graphics |CV, Signal |5.56 |https://www.frontiersin.org/journals/neurorobotics | -|Cognitive Computation |CV |5.24 |https://www.springer.com/journal/40815 | -|International Journal on Document Analysis and Recognition |CV, NLP |4.4 |https://onlinelibrary.wiley.com/journal/10981098 | -|Signal Processing: Image Communication |CV, Signal |3.97 |http://computeroptics.smr.ru/eng/index.html | -|International journal of computer assisted radiology and surgery |CV |3.77 |https://digital-library.theiet.org/content/journals/iet-cvi | -|Journal of Visual Communication and Image Representation |CV, Signal |3.5 |https://www.springer.com/journal/10506 | -|Journal of Imaging |CV |3.43 |??? | -|Computer Optics |CV |3.26 |https://www.springer.com/journal/13042 | -|Information Visualization |CV |3.23 |https://journals.sagepub.com/home/ivi | -|Machine Vision and Applications |CV |3.05 |https://www.journals.elsevier.com/international-journal-of-approximate-reasoning | -|International Journal of Imaging Systems and Technology |CV |2.88 |https://www.journals.elsevier.com/speech-communication | -|Pattern Analysis and Applications |CV, ML |2.76 |https://www.springer.com/journal/13748 | -|Journal of the Optical Society of America A: Optics and Image Science, and Vision |CV |2.25 |https://www.springer.com/journal/10462 | -|Spatial Cognition and Computation |CV |1.88 |https://www.journals.elsevier.com/computers-and-graphics | -|Computers and Graphics |CV, Signal |1.88 |https://www.journals.elsevier.com/artificial-intelligence-in-medicine | -|Journal of Mathematical Imaging and Vision |CV, Comp. Math |1.67 |https://www.springer.com/journal/10514 | -|IET Computer Vision |CV |1.64 |https://tist.acm.org/ | -|Pattern Recognition and Image Analysis |CV, ML |1.24 |https://www.springer.com/journal/11493 | -|Imaging Science Journal |CV |1.17 |https://www.tandfonline.com/loi/yims20 | -|Journal of Computer and Systems Sciences International |CV, ML |1.04 |https://www.springer.com/journal/11488 | -|International Journal of Image and Graphics |CV |0.92 |https://www.worldscientific.com/worldscinet/ijig | -|Intelligent Decision Technologies |CV, ML |0.74 |https://www.iospress.nl/journal/intelligent-decision-technologies/ | -|Information Fusion |Signal |18.92 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=79 | -|IEEE Signal Processing Magazine |Signal |9.72 |https://iopscience.iop.org/journal/0266-5611 | -|Mechanical Systems and Signal Processing |Signal |9.09 |https://benjamins.com/catalog/ijcl | -|IEEE Journal on Selected Topics in Signal Processing |Signal |8.93 |https://www.springer.com/computer/journal/11714?detailsPage=aboutThis | -|IEEE Transactions on Multimedia |Signal |7.27 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6570655 | -|IEEE/ACM Transactions on Audio Speech and Language Processing |Comp. Math, Signal |6.02 |https://tsas.acm.org/ | -|Computer Vision and Image Understanding |CV, Signal |5.53 |https://www.journals.elsevier.com/mathematics-and-computers-in-simulation | -|IEEE Transactions on Signal Processing |Signal |5.27 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=97 | -|Signal Processing |CV, Signal |4.99 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=2945 | -|Image and Vision Computing |CV, Signal |4.63 |https://www.springer.com/journal/40998 | -|Journal of the Franklin Institute |Signal |4.48 |https://ieeexplore.ieee.org/xpl/aboutJournal.jsp?punumber=6884276 | -|APSIPA Transactions on Signal and Information Processing |Signal |4.3 |https://www.ipol.im/ | -|IEEE Transactions on Parallel and Distributed Systems |Comp. Math, Signal |4.3 |https://onlinelibrary.wiley.com/journal/10991115 | -|IEEE Transactions on Control of Network Systems |Signal |3.77 |https://www.springer.com/journal/11760 | -|IEEE Signal Processing Letters |Signal |3.67 |https://jivp-eurasipjournals.springeropen.com | -|IEEE Transactions on Signal and Information Processing over Networks |Signal |3.59 |http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=71 | -|International Journal of Adaptive Control and Signal Processing |Signal |3.54 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=78 | -|Electronics (Switzerland) |Signal |3.27 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=93 | -|Eurasip Journal on Image and Video Processing |Signal |3.24 |https://www.sciencedirect.com/journal/information-fusion | -|Frontiers of Information Technology and Electronic Engineering |Signal |3.05 |https://www.nowpublishers.com/SIG | -|Foundations and Trends in Signal Processing |Signal |3 |https://www.mdpi.com/journal/electronics | -|Circuits, Systems, and Signal Processing |Comp. Math, Signal |2.72 |https://www.springer.com/journal/11128 | -|Multidimensional Systems and Signal Processing |Comp. Math, ML, Signal |2.37 |https://www.springer.com/journal/34 | -|IEEE Multimedia |Signal |2.26 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6046 | -|Iranian Journal of Science and Technology - Transactions of Electrical Engineering |Signal |2.25 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4149689 | -|ACM Transactions on Spatial Algorithms and Systems |Signal |2.23 |https://www.springer.com/journal/11045 | -|IET Image Processing |CV, Signal |2.2 |https://www.sciencedirect.com/journal/computer-vision-and-image-understanding | -|Eurasip Journal on Advances in Signal Processing |Signal |2.1 |https://www.cambridge.org/core/journals/apsipa-transactions-on-signal-and-information-processing | -|IET Signal Processing |Signal |1.99 |http://ieee-iotj.org/ | -|Signal, Image and Video Processing |Signal |1.97 |https://www.sciencedirect.com/journal/journal-of-the-franklin-institute | -|Quantum Information Processing |Signal, Specific |1.91 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6509490 | -|Journal of Signal Processing Systems |Signal |1.87 |https://www.journals.elsevier.com/information-processing-letters | -|Mathematics of Control, Signals, and Systems |Comp. Math, Signal |1.61 |https://www.tandfonline.com/loi/tinf20 | -|Numerical Functional Analysis and Optimization |Comp. Math, Signal |1.43 |https://www.igi-global.com/journal/international-journal-computer-assisted-language/41023 | -|Image Processing On Line |CV, Signal |1.39 |https://www.springer.com/journal/11265 | -|INFOR |Signal |1.27 |https://asp-eurasipjournals.springeropen.com/ | -|Information Processing Letters |Signal |1.14 |https://www.journals.elsevier.com/image-and-vision-computing | -|Computer Assisted Language Learning |NLP |5.74 |https://www.springer.com/journal/10579 | -|Language Learning and Technology |NLP |4.57 |https://www.iospress.nl/journal/applied-ontology/ | -|ReCALL |NLP |4.43 |https://www.lltjournal.org// | -|Journal of Memory and Language |ML, NLP |4.07 |https://www.journals.elsevier.com/computerized-medical-imaging-and-graphics | -|Speech Communication |NLP |4 |https://ieeexplore.ieee.org/xpl/aboutJournal.jsp?punumber=10207 | -|Language Resources and Evaluation |NLP |2.15 |http://www.degruyter.de/journals/cllt/detailEn.cfm | -|Corpus Linguistics and Linguistic Theory |NLP |1.98 |http://www.elsevier.com/wps/find/journaldescription.cws_home/622902/description#description | -|International Journal of Speech Technology |CV, NLP, Signal |1.94 |https://www.cambridge.org/core/journals/recall | -|Applied Ontology |NLP |1.71 |https://www.tandfonline.com/toc/ncal20/current | -|International Journal of Computer-Assisted Language Learning and Teaching |NLP, Specific |1.44 |https://www.worldscientific.com/worldscinet/ijsc | -|International Journal of Corpus Linguistics |NLP |1.13 |https://www.springer.com/journal/10772 | -|International Journal of Semantic Computing |NLP |0.84 |https://www.tandfonline.com/loi/nmcm20 | -|IEEE Internet of Things Journal |CV, ML, Signal, Specific|10.98 |??? | -|IEEE Transactions on Evolutionary Computation |Comp. Math |15.5 |https://www.springer.com/journal/12351/ | -|Applied and Computational Mathematics |Comp. Math |9.25 |https://www.worldscientific.com/worldscinet/aa | -|Archives of Computational Methods in Engineering |Comp. Math |9.18 |https://www.ams.org/publications/journals/journalsframework/tran | -|Journal of Computational Design and Engineering |Comp. Math |6.57 |https://www.ams.org/publications/journals/journalsframework/mcom | -|IEEE Transactions on Knowledge and Data Engineering |Comp. Math |6.09 |https://www.journals.elsevier.com/computational-statistics-and-data-analysis | -|Applied Mathematical Modelling |Comp. Math |5.44 |https://www.journals.elsevier.com/journal-of-informetrics | -|SIAM Review |Comp. Math |4.86 |https://www.springer.com/journal/10588 | -|International Journal of Artificial Intelligence in Education |Comp. Math |4.82 |http://www.ijfis.org/main.html | -|Journal of Numerical Mathematics |Comp. Math |4.76 |https://link.springer.com/journal/40304 | -|Technology, Knowledge and Learning |Comp. Math |4.44 |http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4235 | -|Applied Mathematics and Computation |Comp. Math |4.36 |https://www.springer.com/journal/10208 | -|International Journal of Automation and Computing |Comp. Math |4.28 |https://www.iospress.nl/journal/informatica/ | -|Applied Mathematics Letters |Comp. Math |4.22 |https://www.springer.com/journal/245 | -|Journal of Informetrics |Comp. Math |4.2 |https://www.ams.org/publications/journals/journalsframework/bull | -|Evolutionary Computation |Comp. Math |4.14 |https://www.inderscience.com/jhome.php?jcode=ijcsm | -|Informatica |Comp. Math |3.91 |https://www.ems-ph.org/journals/journal.php?jrn=jems | -|Mathematics and Computers in Simulation |Comp. Math |3.81 |https://www.worldscientific.com/worldscinet/m3as | -|EPJ Data Science |Comp. Math |3.78 |https://www.siam.org/publications/journals/siam-review-sirev | -|Mathematical Models and Methods in Applied Sciences |Comp. Math |3.78 |https://www.springer.com/mathematics/journal/40687 | -|Intelligent Automation and Soft Computing |Comp. Math |3.54 |https://www.springer.com/journal/450 | -|IEEE Transactions on Computers |Comp. Math |3.19 |https://www.springer.com/journal/607 | -|Foundations of Computational Mathematics |Comp. Math |3.12 |https://www.siam.org/publications/journals/siam-journal-on-scientific-computing-sisc | -|Computers and Mathematics with Applications |Comp. Math |3.11 |https://www.tandfonline.com/toc/gcom20/current | -|Computational and Applied Mathematics |Comp. Math |3.09 |https://www.siam.org/publications/journals/siam-journal-on-numerical-analysis-sinum | -|Computational and Mathematical Organization Theory |Comp. Math |3.06 |https://www.tandfonline.com/toc/tsma20/current | -|Computational and Mathematical Methods in Medicine |Comp. Math |3 |https://www.journals.elsevier.com/journal-of-combinatorial-theory-series-a | -|Operational Research |Comp. Math |2.97 |https://www.journals.elsevier.com/journal-of-logical-and-algebraic-methods-in-programming | -|Journal of the American Mathematical Society |Comp. Math |2.95 |https://www.springer.com/journal/11633 | -|International Journal of Computers, Communications and Control |Comp. Math |2.92 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7756 | -|Computing (Vienna/New York) |Comp. Math |2.91 |https://academic.oup.com/imaiai | -|Journal of Computational and Applied Mathematics |Comp. Math |2.87 |https://academic.oup.com/imajna | -|Applied Numerical Mathematics |Comp. Math |2.87 |https://www.journals.elsevier.com/information-and-computation | -|ACM Transactions on Mathematical Software |Comp. Math |2.79 |https://www.mdpi.com/journal/computation | -|Journal of Organizational Computing and Electronic Commerce |Comp. Math |2.76 |https://www.springer.com/journal/11390 | -|SIAM Journal of Scientific Computing |Comp. Math |2.72 |https://www.springer.com/journal/180 | -|Information and Inference |Comp. Math |2.69 |https://www.springer.com/journal/10915 | -|SIAM Journal on Numerical Analysis |Comp. Math |2.69 |https://www.atlantis-press.com/journals/ijcis | -|International Journal of Computational Intelligence Systems |Comp. Math |2.62 |https://www.springer.com/journal/10589 | -|Journal of Scientific Computing |Comp. Math |2.62 |https://www.emerald.com/insight/publication/issn/0264-4401 | -|Computation |Comp. Math |2.55 |https://www.journals.elsevier.com/applied-mathematics-letters | -|International Journal of Data Science and Analytics |Comp. Math |2.52 |https://www.springer.com/journal/10044 | -|Journal of the Brazilian Society of Mechanical Sciences and Engineering |Comp. Math |2.44 |https://www.inderscience.com/jhome.php?jcode=ijmic | -|Bayesian Analysis |Comp. Math, ML |2.42 |https://www.ams.org/publications/journals/journalsframework/jams | -|Revista de la Real Academia de Ciencias Exactas, Fisicas y Naturales - Serie A: Matematicas |Comp. Math |2.42 |https://journals.sagepub.com/home/act | -|Algorithms |Comp. Math |2.36 |http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=69 | -|Journal of Strain Analysis for Engineering Design |Comp. Math |2.33 |https://www.springer.com/journal/10 | -|Methods, Data, Analyses |Comp. Math |2.3 |https://www.springer.com/journal/11950 | -|Journal of Applied Mathematics and Computing |Comp. Math |2.3 |https://www.springer.com/journal/13398 | -|Journal of the European Mathematical Society |Comp. Math |2.29 |https://www.siam.org/publications/journals/siam-journal-on-applied-mathematics-siap | -|International Journal of Intelligent Transportation Systems Research |Comp. Math |2.27 |https://academic.oup.com/jssam | -|International Journal of Applied Mathematics and Computer Science |Comp. Math |2.25 |https://www.global-sci.org/aamm.html | -|Applied Mathematics and Optimization |Comp. Math |2.23 |??? | -|Statistics and Computing |Comp. Math |2.22 |https://www.techscience.com/journal/iasc | -|Numerische Mathematik |Comp. Math |2.22 |https://www.springer.com/journal/12190 | -|Advances in Data Analysis and Classification |Comp. Math |2.22 |https://www.springer.com/journal/10231 | -|Inverse Problems |Comp. Math, Signal |2.22 |https://www.journals.elsevier.com/mechanical-systems-and-signal-processing/ | -|Measurement Science and Technology |Comp. Math |2.21 |https://www.springer.com/journal/10255 | -|Studies in Applied Mathematics |Comp. Math |2.2 |https://www.journals.elsevier.com/applied-mathematical-modelling | -|Optimal Control Applications and Methods |Comp. Math |2.19 |http://acmij.az/view.php?lang=en&menu=0 | -|International Journal of Nonlinear Sciences and Numerical Simulation |Comp. Math |2.18 |https://www.anstuocmath.ro/ | -|Journal of Computer Science and Technology |Comp. Math |2.18 |https://www.springer.com/journal/40593 | -|Concurrency Computation Practice and Experience |Comp. Math |2.18 |https://www.journals.elsevier.com/journal-of-complexity | -|Optimization |Comp. Math |2.17 |https://www.springer.com/journal/11083 | -|IEEE Journal on Multiscale and Multiphysics Computational Techniques |Comp. Math |2.15 |https://msp.org/jomms/about/journal/research.html | -|IMA Journal of Numerical Analysis |Comp. Math |2.14 |https://dl.acm.org/journal/tocl | -|Electrical Engineering |Comp. Math |2.12 |https://www.cambridge.org/core/journals/combinatorics-probability-and-computing | -|Software-Intensive Cyber-Physical Systems |Comp. Math |2.11 |http://univagora.ro/jour/index.php/ijccc/ | -|Journal of Nonlinear and Variational Analysis |Comp. Math |2.07 |https://www.springer.com/journal/10878 | -|ACM Transactions on Parallel Computing |Comp. Math |2.05 |http://mia.ele-math.com/ | -|Smart Science |Comp. Math |2 |https://www.cambridge.org/core/journals/numerical-mathematics-theory-methods-and-applications | -|Advances in Computational Mathematics |Comp. Math |2 |https://www.mitpressjournals.org/loi/evco | -|Journal of Survey Statistics and Methodology |Comp. Math |1.97 |https://www.tandfonline.com/toc/gapa20/current | -|Measurement and Control |Comp. Math |1.97 |https://www.springer.com/journal/894 | -|Distributed Computing |Comp. Math |1.96 |https://www.tandfonline.com/toc/hoce20/current | -|Computational Statistics and Data Analysis |Comp. Math |1.96 |https://www.springer.com/journal/11222 | -|Journal of Molecular Modeling |Comp. Math |1.95 |https://www.journals.elsevier.com/advances-in-applied-mathematics | -|SIAM Journal on Mathematical Analysis |Comp. Math |1.94 |https://www.inderscience.com/jhome.php?jcode=ijcse | -|ESAIM: Mathematical Modelling and Numerical Analysis |Comp. Math |1.94 |https://www.springer.com/journal/365 | -|SIAM Journal on Applied Mathematics |Comp. Math |1.93 |https://dl.acm.org/journal/toms | -|Computational Optimization and Applications |Comp. Math |1.92 |https://www.esaim-m2an.org/ | -|Bulletin of Mathematical Biology |Comp. Math |1.91 |http://www.societyforchaostheory.org/ndpls/ | -|Mathematics of Computation |Comp. Math |1.9 |https://www.esaim-cocv.org/ | -|East Asian Journal on Applied Mathematics |Comp. Math |1.89 |https://www.journals.elsevier.com/operations-research-letters | -|Inverse Problems in Science and Engineering |Comp. Math |1.88 |https://iopscience.iop.org/journal/0957-0233 | -|Analysis and Applications |Comp. Math |1.88 |https://projecteuclid.org/euclid.ba | -|Advances in Calculus of Variations |Comp. Math |1.84 |https://www.springer.com/journal/10623 | -|Measurement |Comp. Math |1.84 |http://pefmath.etf.rs/ | -|ZAMM Zeitschrift fur Angewandte Mathematik und Mechanik |Comp. Math |1.81 |https://www.tandfonline.com/loi/gitr20 | -|Advances in Fuzzy Systems |Comp. Math |1.78 |https://www.springer.com/journal/40314 | -|Bulletin of the American Mathematical Society |Comp. Math |1.76 |http://www.springer.com/engineering/journal/11831 | -|Engineering Computations |Comp. Math |1.74 |https://www.journals.elsevier.com/journal-of-computer-and-system-sciences | -|Journal of Mechanics of Materials and Structures |Comp. Math |1.74 |https://www.springer.com/journal/40315 | -|Journal of Mathematical Behavior |Comp. Math |1.7 |https://www.journals.elsevier.com/journal-of-combinatorial-theory-series-b | -|Nonlinear Analysis, Theory, Methods and Applications |Comp. Math |1.7 |https://www.tandfonline.com/toc/gscs20/current | -|Optimization Methods and Software |Comp. Math |1.69 |https://www.cambridge.org/core/journals/advances-in-applied-probability | -|Communications in Contemporary Mathematics |Comp. Math |1.66 |https://www.springer.com/journal/10114 | -|Computational Thermal Sciences |Comp. Math |1.66 |https://www.aimsciences.org/journal/1078-0947 | -|International Journal of Computer Mathematics |Comp. Math |1.63 |??? | -|Research in Mathematical Sciences |Comp. Math |1.6 |https://onlinelibrary.wiley.com/journal/14679590 | -|IEEE Pervasive Computing |Comp. Math |1.58 |https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=12 | -|Journal of Inverse and Ill-Posed Problems |Comp. Math |1.57 |https://www.amcs.uz.zgora.pl/ | -|Journal of Complexity |Comp. Math |1.57 |http://www.global-sci.org/jcm/ | -|Advances in Computational Design |Comp. Math |1.57 |https://www.journals.elsevier.com/applied-mathematics-and-computation | -|IMA Journal of Management Mathematics |Comp. Math |1.56 |https://www.springer.com/journal/453 | -|International Journal of Computational Methods |Comp. Math |1.54 |https://epjdatascience.springeropen.com/ | -|Computational Statistics |Comp. Math |1.53 |https://www.degruyter.com/view/journals/jnma/jnma-overview.xml | -|Stochastic Processes and their Applications |Comp. Math |1.51 |https://journals.sagepub.com/home/sdj | -|Discrete Optimization |Comp. Math |1.49 |https://www.springer.com/journal/13348 | -|Constructive Approximation |Comp. Math |1.49 |https://www.degruyter.com/view/journals/cmam/cmam-overview.xml | -|IMA Journal of Mathematical Control and Information |Comp. Math |1.48 |http://www.informaworld.com/smpp/title~content=t713640037~db=all | -|Discrete and Continuous Dynamical Systems |Comp. Math |1.47 |https://www.journals.elsevier.com/journal-of-mathematical-analysis-and-applications | -|Stochastic Analysis and Applications |Comp. Math |1.46 |https://www.tandfonline.com/loi/uspp20 | -|ESAIM - Control, Optimisation and Calculus of Variations |Comp. Math |1.45 |https://www.springer.com/journal/10444 | -|Fundamenta Informaticae |Comp. Math |1.44 |https://www.springer.com/journal/446 | -|Designs, Codes, and Cryptography |Comp. Math |1.44 |https://academic.oup.com/imaman | -|International Journal of Innovative Computing, Information and Control |Comp. Math |1.43 |https://www.sciencedirect.com/journal/nonlinear-analysis | -|Journal of Combinatorial Optimization |Comp. Math |1.42 |http://www.aimsciences.org/journal/2155-3289 | -|Applicable Analysis and Discrete Mathematics |Comp. Math |1.4 |https://www.springer.com/journal/40430 | -|Acta Applicandae Mathematicae |Comp. Math |1.4 |https://msp.org/camcos/2019/14-2/ | -|Lifetime Data Analysis |Comp. Math |1.39 |http://www.aftabi.com/DIE/die.html | -|Journal of Combinatorial Theory. Series B |Comp. Math |1.39 |https://www.journals.elsevier.com/discrete-applied-mathematics | -|Integral Transforms and Special Functions |Comp. Math |1.39 |https://www.hindawi.com/journals/cmmm/ | -|Statistics and Public Policy |Comp. Math |1.39 |https://www.springer.com/journal/11538 | -|Journal of Mathematical Analysis and Applications |Comp. Math |1.38 |https://dl.acm.org/journal/topc | -|Journal of Statistical Computation and Simulation |Comp. Math |1.38 |https://www.worldscientific.com/worldscinet/ijwmip | -|Computational Methods in Applied Mathematics |Comp. Math |1.37 |https://www.springer.com/journal/211 | -|International Journal of Wavelets, Multiresolution and Information Processing |Comp. Math |1.37 |https://www.combinatorics.org/ojs/index.php/eljc | -|Advances in Mathematical Physics |Comp. Math |1.36 |https://www.global-sci.org/eajam.html | -|Differential and Integral Equations |Comp. Math |1.36 |??? | -|Zeitschrift fur Analysis und ihre Anwendung |Comp. Math |1.36 |https://www.intlpress.com/site/pub/pages/journals/items/cms/_home/_main/index.php | -|Results in Mathematics |Comp. Math |1.35 |https://www.ejgta.org/index.php/ejgta/index | -|ACM Transactions on Computational Logic |Comp. Math |1.35 |https://www.worldscientific.com/worldscinet/ijcm | -|Transactions of the American Mathematical Society |Comp. Math |1.34 |http://www3.interscience.wiley.com/journal/2133/home | -|International Journal of Computational Science and Engineering |Comp. Math |1.33 |https://www.cambridge.org/core/journals/forum-of-mathematics-sigma | -|Journal of Combinatorial Theory - Series A |Comp. Math |1.32 |https://journals.sagepub.com/home/mac | -|Algorithmica |Comp. Math |1.31 |https://www.tandfonline.com/toc/tmes20/current | -|International Journal of Fuzzy Logic and Intelligent Systems |Comp. Math |1.31 |https://www.worldscientific.com/worldscinet/nmnc | -|Discrete Applied Mathematics |Comp. Math |1.31 |https://www.degruyter.com/view/journals/jiip/jiip-overview.xml | -|Mathematical and Computer Modelling of Dynamical Systems |Comp. Math |1.29 |https://www.springer.com/journal/25 | -|Journal of Pseudo-Differential Operators and Applications |Comp. Math |1.29 |https://academic.oup.com/imamci/ | -|Journal of Computer and System Sciences |Comp. Math |1.29 |https://dl.acm.org/journal/toct | -|Collectanea Mathematica |Comp. Math |1.28 |https://www.aimsciences.org/journal/1930-5311 | -|EURO Journal on Computational Optimization |Comp. Math |1.28 |http://www.techno-press.org/?journal=acd&subpage=5 | -|Ricerche di Matematica |Comp. Math |1.28 |https://www.springer.com/journal/11587 | -|Networks and Heterogeneous Media |Comp. Math |1.27 |https://www.springer.com/journal/11868 | -|AStA Advances in Statistical Analysis |Comp. Math |1.27 |https://www.aimsciences.org/journal/1930-5346 | -|Operations Research Letters |Comp. Math |1.25 |https://www.journals.elsevier.com/discrete-optimization | -|Journal of Logical and Algebraic Methods in Programming |Comp. Math |1.25 |https://www.mdpi.com/journal/algorithms | -|Evolution Equations and Control Theory |Comp. Math |1.24 |https://onlinelibrary.wiley.com/journal/15320634 | -|Journal of Theoretical and Computational Acoustics |Comp. Math |1.24 |https://www.mathos.unios.hr/mc/index.php/mc | -|Theory of Computing |Comp. Math |1.23 |https://www.worldscientific.com/worldscinet/jtca | -|Numerical Algebra, Control and Optimization |Comp. Math |1.22 |https://www.sciencedirect.com/journal/the-journal-of-mathematical-behavior | -|Numerical Mathematics |Comp. Math |1.2 |https://www.siam.org/publications/journals/siam-journal-on-mathematical-analysis-sima | -|Random Structures and Algorithms |Comp. Math |1.2 |https://www.springer.com/journal/11134 | -|Journal of Difference Equations and Applications |Comp. Math |1.19 |http://jnva.biemdas.com/ | -|Mathematical Control and Related Fields |Comp. Math |1.17 |https://www.springer.com/journal/30 | -|Eurasian Journal of Mathematical and Computer Applications |Comp. Math |1.17 |http://www.informaworld.com/smpp/title~content=t713646500~db=all | -|Differential Equations and Dynamical Systems |Comp. Math |1.14 |https://onlinelibrary.wiley.com/journal/10982418 | -|Advances in Differential Equations |Comp. Math |1.13 |http://caim.simai.eu/index.php/caim/index | -|Advances in Applied Probability |Comp. Math |1.13 |https://academic.oup.com/imamat | -|Nonlinear Dynamics, Psychology, and Life Sciences |Comp. Math |1.13 |https://onlinelibrary.wiley.com/journal/14679892 | -|Annali di Matematica Pura ed Applicata |Comp. Math |1.13 |https://www.springer.com/journal/200 | -|Forum of Mathematics, Sigma |Comp. Math |1.12 |https://academic.oup.com/jcde | -|Journal of Statistical Planning and Inference |Comp. Math |1.12 |https://theoryofcomputing.org/ | -|Applicable Analysis |Comp. Math |1.11 |https://www.journals.elsevier.com/journal-of-approximation-theory | -|Advances in Applied Mathematics |Comp. Math |1.1 |https://www.springer.com/journal/454 | -|Nonlinear Differential Equations and Applications |Comp. Math |1.09 |https://www.degruyter.com/view/j/demo | -|International Journal of Mathematical Education in Science and Technology |Comp. Math |1.08 |https://www.springer.com/journal/224 | -|Journal of Approximation Theory |Comp. Math |1.08 |https://www.aimsciences.org/journal/2156-8472 | -|Journal of Time Series Analysis |Comp. Math |1.07 |https://journals.math.tku.edu.tw/index.php/TKJM | -|Journal of Algorithms and Computational Technology |Comp. Math |1.07 |https://link.springer.com/journal/13675 | -|Communications in Mathematical Biology and Neuroscience |Comp. Math |1.05 |https://www.tandfonline.com/toc/gipe20/current | -|Communications in Mathematical Sciences |Comp. Math |1.05 |https://www.journals.elsevier.com/stochastic-processes-and-their-applications | -|New Mathematics and Natural Computation |Comp. Math |1.04 |https://www.springer.com/education+%26+language/learning+%26+instruction/journal/10758 | -|International Journal of Grid and Utility Computing |Comp. Math |1.04 |https://academic.oup.com/qjmam | -|Quarterly of Applied Mathematics |Comp. Math |1.03 |https://www.aimsciences.org/journal/1556-1801 | -|Advances in Applied Mathematics and Mechanics |Comp. Math |1.03 |https://www.worldscientific.com/worldscinet/ccm | -|Quarterly Journal of Mechanics and Applied Mathematics |Comp. Math |1.02 |https://www.ams.org/publications/journals/journalsframework/proc | -|Information and Computation |Comp. Math |1.01 |https://www.iospress.nl/journal/fundamenta-informaticae/ | -|Journal of Symbolic Computation |Comp. Math |1.01 |https://www.journals.elsevier.com/journal-of-computational-and-applied-mathematics | -|Analele Stiintifice ale Universitatii Ovidius Constanta, Seria Matematica |Comp. Math |1.01 |https://www.hindawi.com/journals/amp/ | -|Aequationes Mathematicae |Comp. Math |1.01 |https://www.degruyter.com/view/j/form | -|Advances in Mathematics of Communications |Comp. Math |1.01 |https://www.degruyter.com/view/j/agms | -|Computational Methods and Function Theory |Comp. Math |1.01 |http://ejmca.enu.kz/ | -|Communications in Applied Mathematics and Computational Science |Comp. Math |1 |https://www.ams.org/publications/journals/journalsframework/qam | -|Analysis and Geometry in Metric Spaces |Comp. Math |1 |https://ieee-jmmct.org/ | -|Mathematical Inequalities and Applications |Comp. Math |1 |https://www.inderscience.com/jhome.php?jcode=ijguc | -|Queueing Systems |Comp. Math |1 |https://www.springer.com/journal/11786 | -|IMA Journal of Applied Mathematics |Comp. Math |0.99 |http://www.aftabi.com/ADE/ade.html | -|Journal of Computational Mathematics |Comp. Math |0.98 |https://www.journals.elsevier.com/journal-of-statistical-planning-and-inference | -|Tamkang Journal of Mathematics |Comp. Math |0.98 |https://www.springer.com/journal/10182 | -|Forum Mathematicum |Comp. Math |0.97 |http://www.springer.com/engineering/electronics/journal/202 | -|Proceedings of the American Mathematical Society |Comp. Math |0.96 |https://www.springer.com/journal/12591 | -|Vestnik Sankt-Peterburgskogo Universiteta, Prikladnaya Matematika, Informatika, Protsessy Upravleniya |Comp. Math |0.95 |https://mda.gesis.org/index.php/mda/index | -|Mathematical Communications |Comp. Math |0.95 |https://onlinelibrary.wiley.com/journal/15214001 | -|European Journal of Applied Mathematics |Comp. Math |0.94 |https://www.tandfonline.com/toc/lsaa20/current | -|Qualitative Theory of Dynamical Systems |Comp. Math |0.92 |https://www.springer.com/journal/10985 | -|European Journal of Combinatorics |Comp. Math |0.92 |https://www.tandfonline.com/toc/goms20/current | -|Communications in Applied and Industrial Mathematics |Comp. Math |0.92 |https://www.cambridge.org/core/journals/european-journal-of-applied-mathematics | -|Discrete and Computational Geometry |Comp. Math |0.89 |https://www.journals.elsevier.com/european-journal-of-combinatorics | -|ACM Transactions on Computation Theory |Comp. Math |0.88 |https://www.journals.elsevier.com/computers-and-mathematics-with-applications | -|Combinatorics Probability and Computing |Comp. Math |0.87 |https://www.tandfonline.com/toc/hmes20/current | -|Computing and Informatics |Comp. Math |0.87 |http://www.compama.co.usb.ve/ | -|International Journal of Computing Science and Mathematics |Comp. Math |0.86 |http://www.hindawi.com/journals/afs/ | -|Theory of Computing Systems |Comp. Math |0.84 |https://www.ems-ph.org/journals/journal.php?jrn=zaa | -|Bulletin of the South Ural State University, Series: Mathematical Modelling, Programming and Computer Software|Comp. Math |0.83 |http://www.apmath.spbu.ru/ru/resource/vestnik/ | -|Applied Mathematics |Comp. Math |0.8 |https://www.degruyter.com/view/j/jaa?lang=en | -|International Journal of Modelling, Identification and Control |Comp. Math |0.8 |https://www.springer.com/journal/10440 | -|Acta Mathematica Sinica, English Series |Comp. Math |0.8 |https://www.springer.com/engineering/electronics/journal/13177 | -|Applied Mathematics E - Notes |Comp. Math |0.79 |https://mmp.susu.ru/page/en/greet | -|Bulletin of Computational Applied Mathematics |Comp. Math |0.78 |http://www.math.nthu.edu.tw/~amen/ | -|Order |Comp. Math |0.76 |https://www.begellhouse.com/journals/computational-thermal-sciences.html | -|Communications in Mathematics and Statistics |Comp. Math |0.73 |https://www.journals.elsevier.com/applied-numerical-mathematics/ | -|Applicable Algebra in Engineering, Communications and Computing |Comp. Math |0.72 |??? | -|Journal of Modern Dynamics |Comp. Math |0.68 |https://www.springer.com/journal/12346 | -|Journal of Applied Analysis |Comp. Math |0.67 |http://www.cai.sk/ojs/index.php/cai | -|Electronic Journal of Graph Theory and Applications |Comp. Math |0.66 |https://mcfns.net/index.php/Journal | -|Electronic Journal of Combinatorics |Comp. Math |0.63 |??? | -|Acta Mathematicae Applicatae Sinica |Comp. Math |0.62 |https://www.degruyter.com/view/journals/acv/acv-overview.xml | -|Mathematics in Computer Science |Comp. Math |0.54 |https://www.springer.com/journal/11634 | -|Dependence Modeling |Comp. Math |0.52 |https://www.aimsciences.org/journal/A0000-0000 | -|Journal of Computational Methods in Sciences and Engineering |Comp. Math |0.48 |https://www.springer.com/journal/11766 | -|Mathematical and Computational Forestry and Natural-Resource Sciences |Comp. Math |0.47 |https://www.degruyter.com/view/journals/ijnsns/ijnsns-overview.xml | -|Journal of Applied Mathematics and Informatics |Comp. Math |0.47 |https://www.iospress.nl/journal/journal-of-computational-methods-in-sciences-and-engineering/ | +| Journal name | Category | Impact | URL | +| -------------------------------------------------------------------------------------------------------------- | ------------------------ | ------ | ------------------------------------------------------------------------------------------------------------- | +| Foundations and Trends in Machine Learning | ML | 38.78 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34 | +| International Journal of Information Management | ML | 21.35 | https://robotics.sciencemag.org/ | +| Science Robotics | ML, Specific | 17.02 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=9670 | +| IEEE Transactions on Pattern Analysis and Machine Intelligence | CV, Comp. Math, ML | 15.84 | https://www.journals.elsevier.com/signal-processing | +| Nature Machine Intelligence | ML | 13.63 | https://www.frontiersin.org/journals/robotics-and-ai | +| Artificial Intelligence Review | ML, NLP | 11.67 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6570654 | +| IEEE Transactions on Neural Networks and Learning Systems | ML | 10.47 | https://www.osapublishing.org/josaa/home.cfm | +| IEEE Transactions on Fuzzy Systems | Comp. Math, ML | 10.12 | https://www.springer.com/journal/521 | +| ACM Transactions on Intelligent Systems and Technology | ML | 9.9 | https://www.springer.com/journal/11721 | +| Neural Networks | ML | 9.7 | https://www.journals.elsevier.com/neurocomputing | +| Expert Systems with Applications | ML | 9.6 | https://www.springer.com/journal/12559 | +| International Journal of Intelligent Systems | ML | 9.34 | https://www.comsoc.org/publications/journals/ieee-tccn | +| Soft Robotics | ML, Specific | 9.22 | http://www.jmlr.org/ | +| Journal of Intelligent Manufacturing | ML | 9.18 | https://www.journals.elsevier.com/international-journal-of-information-management/ | +| CAAI Transactions on Intelligence Technology | ML | 9.11 | ??? | +| Knowledge-Based Systems | ML | 8.66 | https://www.sciencedirect.com/journal/pattern-recognition | +| Engineering Applications of Artificial Intelligence | ML | 8.64 | https://www.journals.elsevier.com/digital-signal-processing | +| Pattern Recognition | CV, ML, NLP, Signal | 8.54 | https://www.springer.com/journal/11548 | +| Advanced Engineering Informatics | ML | 8.53 | https://link.springer.com/journal/10845 | +| Information Sciences | ML | 8.51 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6221037 | +| Artificial Intelligence in Medicine | ML, Specific | 8.3 | https://www.journals.elsevier.com/neural-networks | +| IEEE/CAA Journal of Automatica Sinica | ML | 7.7 | https://onlinelibrary.wiley.com/journal/14680394 | +| International Journal of Robotics Research | ML, Specific | 7.38 | https://onlinelibrary.wiley.com/journal/1098111x | +| IEEE Transactions on Cognitive Communications and Networking | ML | 7.12 | https://www.journals.elsevier.com/fuzzy-sets-and-systems | +| Neurocomputing | ML | 6.19 | https://www.springer.com/journal/10115 | +| Fuzzy Optimization and Decision Making | ML | 6.06 | http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=91 | +| Cognitive Systems Research | ML | 5.99 | https://www.springer.com/journal/10951 | +| Minds and Machines | ML | 5.92 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7274989 | +| IEEE Intelligent Systems | ML | 5.82 | http://www.elsevier.com/wps/find/journaldescription.cws_home/505651/description#description | +| IEEE Computational Intelligence Magazine | ML | 5.71 | https://www.mdpi.com/journal/jimaging | +| Pattern Recognition Letters | CV, ML, NLP, Signal | 5.67 | https://www.springer.com/journal/10700 | +| Computational Linguistics | ML, NLP | 5.63 | http://journals.cambridge.org/action/displayJournal?jid=NLE | +| Neural Computing and Applications | ML | 5.6 | https://www.journals.elsevier.com/journal-of-memory-and-language | +| Artificial Intelligence | ML, NLP | 5.57 | https://www.sciencedirect.com/journal/medical-image-analysis | +| Applied Intelligence | ML | 5.44 | https://www.journals.elsevier.com/knowledge-based-systems | +| Integrated Computer-Aided Engineering | Comp. Math, ML | 5.44 | http://online.liebertpub.com/soro | +| Journal of Machine Learning Research | ML | 5.41 | https://journals.sagepub.com/home/ijr | +| Journal of Parallel and Distributed Computing | ML, Specific | 5.27 | https://www.tandfonline.com/toc/teta20/current | +| Progress in Artificial Intelligence | ML | 5.2 | https://www.springer.com/journal/10339 | +| Artificial Intelligence and Law | ML, Specific | 4.94 | https://www.springer.com/journal/10851 | +| Fuzzy Sets and Systems | ML | 4.76 | https://www.journals.elsevier.com/artificial-intelligence/ | +| ACM Transactions on Human-Robot Interaction | ML | 4.69 | ??? | +| International Journal of Machine Learning and Cybernetics | CV, ML | 4.66 | https://www.iospress.nl/journal/integrated-computer-aided-engineering/ | +| Journal of Artificial Intelligence and Soft Computing Research | CV, ML | 4.62 | https://www.tandfonline.com/toc/hscc20/current | +| IEEE Transactions on Human-Machine Systems | ML, Signal | 4.6 | https://www.journals.elsevier.com/engineering-applications-of-artificial-intelligence | +| Machine Learning | ML | 4.54 | https://dl.acm.org/journal/tcps | +| Design Studies | ML, Specific | 4.36 | https://www.springer.com/journal/41315 | +| International Journal of Approximate Reasoning | ML, Specific | 4.31 | https://www.hindawi.com/journals/acisc/ | +| International Journal of Fuzzy Systems | Comp. Math, ML | 4.23 | https://www.journals.elsevier.com/advanced-engineering-informatics | +| Frontiers in Neurorobotics | ML, Specific | 4.08 | http://www.springer.com/computer+science/ai/journal/10489 | +| Applied Computational Intelligence and Soft Computing | ML | 4.07 | https://journals.sagepub.com/home/arx | +| Network Neuroscience | ML | 4.07 | https://www.springer.com/journal/11067 | +| Autonomous Robots | ML, Specific | 3.94 | https://www.springer.com/journal/10032 | +| Big Data and Cognitive Computing | ML | 3.9 | https://www.springer.com/journal/498 | +| Journal of Intelligent and Robotic Systems: Theory and Applications | ML, Specific | 3.61 | https://www.springer.com/journal/10601 | +| Journal of Artificial Intelligence Research | ML | 3.59 | https://www.journals.elsevier.com/expert-systems-with-applications | +| Frontiers in Robotics and AI | ML | 3.47 | ??? | +| IEEE Transactions on Cognitive and Developmental Systems | ML | 3.45 | https://onlinelibrary.wiley.com/journal/17568765 | +| Robotics | ML, Specific | 3.4 | https://dl.acm.org/journal/jacm | +| Autonomous Agents and Multi-Agent Systems | ML | 3.38 | ??? | +| Swarm Intelligence | ML, Specific | 3.31 | https://www.journals.elsevier.com/information-sciences | +| Intelligent Service Robotics | ML, Specific | 3.15 | https://www.mitpressjournals.org/netn | +| Digital Signal Processing: A Review Journal | Comp. Math, ML, Signal | 3.15 | http://jaiscr.eu/ | +| Expert Systems | Comp. Math, ML | 3.09 | https://www.jair.org/index.php/jair | +| ACM Transactions on Cyber-Physical Systems | ML | 3.08 | http://www.springer.com/computer+science/ai/journal/11063 | +| Knowledge and Information Systems | ML | 3.06 | https://link.springer.com/journal/11263 | +| Computational Intelligence | Comp. Math, ML | 3.02 | https://www.springer.com/journal/10458 | +| Evolutionary Intelligence | ML | 2.96 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=5962385 | +| Journal of Intelligent Information Systems | ML | 2.94 | https://www.mitpressjournals.org/loi/coli | +| Applied Artificial Intelligence | ML | 2.92 | http://www.computability.de/journal/ | +| AI and Society | ML | 2.87 | https://www.iospress.nl/journal/argument-computation/ | +| Journal of the ACM | ML | 2.87 | https://www.journals.elsevier.com/design-studies | +| AI Magazine | ML | 2.87 | https://www.springer.com/journal/10844 | +| Journal of Experimental and Theoretical Artificial Intelligence | ML | 2.85 | https://www.springer.com/journal/10732 | +| Systems Science and Control Engineering | ML | 2.8 | http://www.actapress.com/Content_of_Journal.aspx?JournalID=119 | +| Neural Processing Letters | ML | 2.8 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4200690 | +| Topics in Cognitive Science | ML | 2.74 | https://www.cambridge.org/core/journals/theory-and-practice-of-logic-programming | +| Applied System Innovation | ML, Specific | 2.73 | https://www.journals.elsevier.com/physics-of-life-reviews | +| IET Cyber-Physical Systems: Theory and Applications | ML | 2.72 | https://www.springer.com/journal/10590 | +| ACM Transactions on Interactive Intelligent Systems | ML | 2.47 | https://www.springer.com/journal/11023 | +| Networks and Spatial Economics | ML, Specific | 2.4 | https://www.springer.com/journal/10846 | +| Knowledge Engineering Review | ML | 2.39 | https://www.springer.com/journal/11370 | +| Physics of Life Reviews | Comp. Math, ML, Specific | 2.38 | https://www.nowpublishers.com/MAL | +| Kybernetes | ML | 2.38 | http://ijfs.usb.ac.ir/ | +| Cognitive Science | ML | 2.35 | https://www.emerald.com/insight/publication/issn/0368-492X | +| Argument and Computation | Comp. Math, ML | 2.28 | https://www.iospress.nl/journal/international-journal-of-knowledge-based-and-intelligent-engineering-systems/ | +| Cybernetics and Systems | ML | 2.24 | https://www.mdpi.com/journal/robotics | +| Iranian Journal of Fuzzy Systems | ML, Specific | 2.24 | https://www.sciencedirect.com/journal/journal-of-parallel-and-distributed-computing | +| Journal of Heuristics | ML | 2.24 | https://www.springer.com/journal/10994 | +| Journal of Scheduling | ML | 2.2 | http://journals.cambridge.org/action/displayJournal?jid=KER | +| IEEE Transactions on Games | ML, Specific | 2.18 | https://onlinelibrary.wiley.com/journal/14678640 | +| Journal of Intelligent Systems | ML | 2.16 | https://www.springer.com/journal/146 | +| International Journal of Advanced Robotic Systems | ML | 2.15 | https://www.springer.com/journal/10817 | +| Machine Translation | ML, NLP | 2.15 | ??? | +| Journal of Pragmatics | ML | 2.11 | https://www.tandfonline.com/toc/uaai20/current | +| Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM | ML | 2.04 | http://www.ijfis.org/main.html | +| Natural Language Engineering | ML, NLP | 2.03 | https://onlinelibrary.wiley.com/journal/15516709 | +| Spatial Information Research | ML | 2 | ??? | +| Journal of Intelligent and Fuzzy Systems | ML, Specific | 1.95 | https://www.tandfonline.com/toc/ucbs20/current | +| KI - Kunstliche Intelligenz | ML | 1.91 | https://www.degruyter.com/view/journals/jisys/jisys-overview.xml | +| International Journal of Swarm Intelligence Research | ML | 1.86 | https://academic.oup.com/jos | +| International Journal of Intelligent Robotics and Applications | ML | 1.81 | https://dl.acm.org/journal/tiis | +| Theory and Practice of Logic Programming | Comp. Math, ML | 1.73 | https://aaai.org/Magazine/magazine.php | +| International Journal of Knowledge and Systems Science | ML | 1.69 | https://www.tandfonline.com/loi/lnfa20 | +| Journal on Data Semantics | CV, ML, NLP, Signal | 1.68 | http://www.nnw.cz/ | +| International Journal of Pattern Recognition and Artificial Intelligence | CV, ML | 1.67 | https://www.worldscientific.com/worldscinet/ijait | +| Journal of Automated Reasoning | Comp. Math, ML, Specific | 1.66 | https://www.journals.elsevier.com/cognitive-systems-research | +| Bulletin of the Polish Academy of Sciences: Technical Sciences | ML | 1.66 | https://www.journals.elsevier.com/journal-of-pragmatics | +| International Journal of Humanoid Robotics | ML, Specific | 1.6 | https://www.worldscientific.com/worldscinet/ijprai | +| Neural Network World | ML | 1.57 | https://www.fujipress.jp/jaciii/jc/ | +| Cognitive Processing | ML | 1.45 | https://www.worldscientific.com/worldscinet/ijufks | +| Adaptive Behavior | ML | 1.44 | https://www.worldscientific.com/worldscinet/ijhr | +| AI Communications | ML | 1.37 | http://journals.pan.pl/dlibra/journal/119067 | +| International Journal of Software Innovation | ML | 1.34 | https://journal.iberamia.org/index.php/intartif/index | +| International Journal on Artificial Intelligence Tools | ML | 1.33 | https://www.worldscientific.com/worldscinet/ijseke | +| International Journal of Fuzzy Logic and Intelligent Systems | ML | 1.31 | http://www.springer.com/computer+science/ai/journal/10472 | +| International Journal of Software Engineering and Knowledge Engineering | ML | 1.31 | https://www.aicommunications.eu/ | +| Intelligent Data Analysis | CV, ML | 1.3 | https://www.tandfonline.com/loi/tfie20 | +| Annals of Mathematics and Artificial Intelligence | Comp. Math, ML | 1.3 | https://journals.sagepub.com/home/adb | +| International Journal of Robotics and Automation | ML, Specific | 1.25 | https://www.iospress.nl/journal/intelligent-data-analysis/ | +| Informatica (Slovenia) | ML | 1.21 | https://www.worldscientific.com/worldscinet/ijsc | +| International Journal of Cognitive Informatics and Natural Intelligence | ML | 1.19 | ??? | +| Parallel Computing | ML | 1.16 | ??? | +| International Journal of Uncertainty, Fuzziness and Knowlege-Based Systems | ML | 1.15 | https://www.journals.elsevier.com/parallel-computing | +| Intelligenza Artificiale | ML | 1.13 | https://www.kybernetika.cz/ | +| Journal of Semantics | ML | 1.12 | https://constructivist.info/ | +| Inteligencia Artificial | ML | 0.95 | https://www.igi-global.com/journal/international-journal-swarm-intelligence-research/1149 | +| Web Intelligence | ML | 0.95 | https://www.springer.com/journal/10015 | +| Automatic Control and Computer Sciences | Comp. Math, ML | 0.93 | https://digital-library.theiet.org/content/journals/iet-spr | +| Constraints | Comp. Math, ML | 0.88 | https://www.iospress.nl/journal/journal-of-intelligent-fuzzy-systems/ | +| IEICE Transactions on Information and Systems | ML | 0.88 | https://journals.agh.edu.pl/csci | +| International Journal of Semantic Computing | ML | 0.84 | https://www.jstage.jst.go.jp/browse/transinf | +| Artificial Life and Robotics | ML | 0.84 | https://www.iospress.nl/journal/intelligenza-artificiale/ | +| Computer Science | ML | 0.83 | https://www.iospress.nl/journal/web-intelligence-and-agent-systems/ | +| International Journal of Knowledge-Based and Intelligent Engineering Systems | ML | 0.81 | http://journals.cambridge.org/action/displayJournal?jid=AIE | +| Kybernetika | ML | 0.8 | http://cogsci.snu.ac.kr/jcs/ | +| Computability | Comp. Math, ML | 0.71 | https://www.springer.com/computer/database+management+%26+information+retrieval/journal/13740 | +| Journal of Advanced Computational Intelligence and Intelligent Informatics | ML | 0.53 | https://www.igi-global.com/journal/international-journal-software-innovation/64245 | +| Journal of Robotics, Networking and Artificial Life | ML | 0.49 | ??? | +| Fuzzy Information and Engineering | ML | 0.45 | http://www.informatica.si/index.php/informatica | +| Computer Science Journal of Moldova | ML | 0.43 | https://www.igi-global.com/journal/international-journal-knowledge-systems-science/1169 | +| Journal of Cognitive Science | ML | 0.39 | https://www.igi-global.com/journal/international-journal-cognitive-informatics-natural/1095 | +| Constructivist Foundations | ML | 0.36 | https://www.tandfonline.com/action/journalInformation?journalCode=tssc20 | +| Medical Image Analysis | CV, Specific | 15.24 | https://www.journals.elsevier.com/journal-of-visual-communication-and-image-representation | +| International Journal of Computer Vision | CV, ML | 11.81 | https://www.journals.elsevier.com/pattern-recognition-letters | +| Computerized Medical Imaging and Graphics | CV | 8.4 | https://www.springer.com/journal/12065 | +| IEEE Transactions on Visualization and Computer Graphics | CV, Signal | 5.56 | https://www.frontiersin.org/journals/neurorobotics | +| Cognitive Computation | CV | 5.24 | https://www.springer.com/journal/40815 | +| International Journal on Document Analysis and Recognition | CV, NLP | 4.4 | https://onlinelibrary.wiley.com/journal/10981098 | +| Signal Processing: Image Communication | CV, Signal | 3.97 | http://computeroptics.smr.ru/eng/index.html | +| International journal of computer assisted radiology and surgery | CV | 3.77 | https://digital-library.theiet.org/content/journals/iet-cvi | +| Journal of Visual Communication and Image Representation | CV, Signal | 3.5 | https://www.springer.com/journal/10506 | +| Journal of Imaging | CV | 3.43 | ??? | +| Computer Optics | CV | 3.26 | https://www.springer.com/journal/13042 | +| Information Visualization | CV | 3.23 | https://journals.sagepub.com/home/ivi | +| Machine Vision and Applications | CV | 3.05 | https://www.journals.elsevier.com/international-journal-of-approximate-reasoning | +| International Journal of Imaging Systems and Technology | CV | 2.88 | https://www.journals.elsevier.com/speech-communication | +| Pattern Analysis and Applications | CV, ML | 2.76 | https://www.springer.com/journal/13748 | +| Journal of the Optical Society of America A: Optics and Image Science, and Vision | CV | 2.25 | https://www.springer.com/journal/10462 | +| Spatial Cognition and Computation | CV | 1.88 | https://www.journals.elsevier.com/computers-and-graphics | +| Computers and Graphics | CV, Signal | 1.88 | https://www.journals.elsevier.com/artificial-intelligence-in-medicine | +| Journal of Mathematical Imaging and Vision | CV, Comp. Math | 1.67 | https://www.springer.com/journal/10514 | +| IET Computer Vision | CV | 1.64 | https://tist.acm.org/ | +| Pattern Recognition and Image Analysis | CV, ML | 1.24 | https://www.springer.com/journal/11493 | +| Imaging Science Journal | CV | 1.17 | https://www.tandfonline.com/loi/yims20 | +| Journal of Computer and Systems Sciences International | CV, ML | 1.04 | https://www.springer.com/journal/11488 | +| International Journal of Image and Graphics | CV | 0.92 | https://www.worldscientific.com/worldscinet/ijig | +| Intelligent Decision Technologies | CV, ML | 0.74 | https://www.iospress.nl/journal/intelligent-decision-technologies/ | +| Information Fusion | Signal | 18.92 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=79 | +| IEEE Signal Processing Magazine | Signal | 9.72 | https://iopscience.iop.org/journal/0266-5611 | +| Mechanical Systems and Signal Processing | Signal | 9.09 | https://benjamins.com/catalog/ijcl | +| IEEE Journal on Selected Topics in Signal Processing | Signal | 8.93 | https://www.springer.com/computer/journal/11714?detailsPage=aboutThis | +| IEEE Transactions on Multimedia | Signal | 7.27 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6570655 | +| IEEE/ACM Transactions on Audio Speech and Language Processing | Comp. Math, Signal | 6.02 | https://tsas.acm.org/ | +| Computer Vision and Image Understanding | CV, Signal | 5.53 | https://www.journals.elsevier.com/mathematics-and-computers-in-simulation | +| IEEE Transactions on Signal Processing | Signal | 5.27 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=97 | +| Signal Processing | CV, Signal | 4.99 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=2945 | +| Image and Vision Computing | CV, Signal | 4.63 | https://www.springer.com/journal/40998 | +| Journal of the Franklin Institute | Signal | 4.48 | https://ieeexplore.ieee.org/xpl/aboutJournal.jsp?punumber=6884276 | +| APSIPA Transactions on Signal and Information Processing | Signal | 4.3 | https://www.ipol.im/ | +| IEEE Transactions on Parallel and Distributed Systems | Comp. Math, Signal | 4.3 | https://onlinelibrary.wiley.com/journal/10991115 | +| IEEE Transactions on Control of Network Systems | Signal | 3.77 | https://www.springer.com/journal/11760 | +| IEEE Signal Processing Letters | Signal | 3.67 | https://jivp-eurasipjournals.springeropen.com | +| IEEE Transactions on Signal and Information Processing over Networks | Signal | 3.59 | http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=71 | +| International Journal of Adaptive Control and Signal Processing | Signal | 3.54 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=78 | +| Electronics (Switzerland) | Signal | 3.27 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=93 | +| Eurasip Journal on Image and Video Processing | Signal | 3.24 | https://www.sciencedirect.com/journal/information-fusion | +| Frontiers of Information Technology and Electronic Engineering | Signal | 3.05 | https://www.nowpublishers.com/SIG | +| Foundations and Trends in Signal Processing | Signal | 3 | https://www.mdpi.com/journal/electronics | +| Circuits, Systems, and Signal Processing | Comp. Math, Signal | 2.72 | https://www.springer.com/journal/11128 | +| Multidimensional Systems and Signal Processing | Comp. Math, ML, Signal | 2.37 | https://www.springer.com/journal/34 | +| IEEE Multimedia | Signal | 2.26 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6046 | +| Iranian Journal of Science and Technology - Transactions of Electrical Engineering | Signal | 2.25 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4149689 | +| ACM Transactions on Spatial Algorithms and Systems | Signal | 2.23 | https://www.springer.com/journal/11045 | +| IET Image Processing | CV, Signal | 2.2 | https://www.sciencedirect.com/journal/computer-vision-and-image-understanding | +| Eurasip Journal on Advances in Signal Processing | Signal | 2.1 | https://www.cambridge.org/core/journals/apsipa-transactions-on-signal-and-information-processing | +| IET Signal Processing | Signal | 1.99 | http://ieee-iotj.org/ | +| Signal, Image and Video Processing | Signal | 1.97 | https://www.sciencedirect.com/journal/journal-of-the-franklin-institute | +| Quantum Information Processing | Signal, Specific | 1.91 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6509490 | +| Journal of Signal Processing Systems | Signal | 1.87 | https://www.journals.elsevier.com/information-processing-letters | +| Mathematics of Control, Signals, and Systems | Comp. Math, Signal | 1.61 | https://www.tandfonline.com/loi/tinf20 | +| Numerical Functional Analysis and Optimization | Comp. Math, Signal | 1.43 | https://www.igi-global.com/journal/international-journal-computer-assisted-language/41023 | +| Image Processing On Line | CV, Signal | 1.39 | https://www.springer.com/journal/11265 | +| INFOR | Signal | 1.27 | https://asp-eurasipjournals.springeropen.com/ | +| Information Processing Letters | Signal | 1.14 | https://www.journals.elsevier.com/image-and-vision-computing | +| Computer Assisted Language Learning | NLP | 5.74 | https://www.springer.com/journal/10579 | +| Language Learning and Technology | NLP | 4.57 | https://www.iospress.nl/journal/applied-ontology/ | +| ReCALL | NLP | 4.43 | https://www.lltjournal.org// | +| Journal of Memory and Language | ML, NLP | 4.07 | https://www.journals.elsevier.com/computerized-medical-imaging-and-graphics | +| Speech Communication | NLP | 4 | https://ieeexplore.ieee.org/xpl/aboutJournal.jsp?punumber=10207 | +| Language Resources and Evaluation | NLP | 2.15 | http://www.degruyter.de/journals/cllt/detailEn.cfm | +| Corpus Linguistics and Linguistic Theory | NLP | 1.98 | http://www.elsevier.com/wps/find/journaldescription.cws_home/622902/description#description | +| International Journal of Speech Technology | CV, NLP, Signal | 1.94 | https://www.cambridge.org/core/journals/recall | +| Applied Ontology | NLP | 1.71 | https://www.tandfonline.com/toc/ncal20/current | +| International Journal of Computer-Assisted Language Learning and Teaching | NLP, Specific | 1.44 | https://www.worldscientific.com/worldscinet/ijsc | +| International Journal of Corpus Linguistics | NLP | 1.13 | https://www.springer.com/journal/10772 | +| International Journal of Semantic Computing | NLP | 0.84 | https://www.tandfonline.com/loi/nmcm20 | +| IEEE Internet of Things Journal | CV, ML, Signal, Specific | 10.98 | ??? | +| IEEE Transactions on Evolutionary Computation | Comp. Math | 15.5 | https://www.springer.com/journal/12351/ | +| Applied and Computational Mathematics | Comp. Math | 9.25 | https://www.worldscientific.com/worldscinet/aa | +| Archives of Computational Methods in Engineering | Comp. Math | 9.18 | https://www.ams.org/publications/journals/journalsframework/tran | +| Journal of Computational Design and Engineering | Comp. Math | 6.57 | https://www.ams.org/publications/journals/journalsframework/mcom | +| IEEE Transactions on Knowledge and Data Engineering | Comp. Math | 6.09 | https://www.journals.elsevier.com/computational-statistics-and-data-analysis | +| Applied Mathematical Modelling | Comp. Math | 5.44 | https://www.journals.elsevier.com/journal-of-informetrics | +| SIAM Review | Comp. Math | 4.86 | https://www.springer.com/journal/10588 | +| International Journal of Artificial Intelligence in Education | Comp. Math | 4.82 | http://www.ijfis.org/main.html | +| Journal of Numerical Mathematics | Comp. Math | 4.76 | https://link.springer.com/journal/40304 | +| Technology, Knowledge and Learning | Comp. Math | 4.44 | http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4235 | +| Applied Mathematics and Computation | Comp. Math | 4.36 | https://www.springer.com/journal/10208 | +| International Journal of Automation and Computing | Comp. Math | 4.28 | https://www.iospress.nl/journal/informatica/ | +| Applied Mathematics Letters | Comp. Math | 4.22 | https://www.springer.com/journal/245 | +| Journal of Informetrics | Comp. Math | 4.2 | https://www.ams.org/publications/journals/journalsframework/bull | +| Evolutionary Computation | Comp. Math | 4.14 | https://www.inderscience.com/jhome.php?jcode=ijcsm | +| Informatica | Comp. Math | 3.91 | https://www.ems-ph.org/journals/journal.php?jrn=jems | +| Mathematics and Computers in Simulation | Comp. Math | 3.81 | https://www.worldscientific.com/worldscinet/m3as | +| EPJ Data Science | Comp. Math | 3.78 | https://www.siam.org/publications/journals/siam-review-sirev | +| Mathematical Models and Methods in Applied Sciences | Comp. Math | 3.78 | https://www.springer.com/mathematics/journal/40687 | +| Intelligent Automation and Soft Computing | Comp. Math | 3.54 | https://www.springer.com/journal/450 | +| IEEE Transactions on Computers | Comp. Math | 3.19 | https://www.springer.com/journal/607 | +| Foundations of Computational Mathematics | Comp. Math | 3.12 | https://www.siam.org/publications/journals/siam-journal-on-scientific-computing-sisc | +| Computers and Mathematics with Applications | Comp. Math | 3.11 | https://www.tandfonline.com/toc/gcom20/current | +| Computational and Applied Mathematics | Comp. Math | 3.09 | https://www.siam.org/publications/journals/siam-journal-on-numerical-analysis-sinum | +| Computational and Mathematical Organization Theory | Comp. Math | 3.06 | https://www.tandfonline.com/toc/tsma20/current | +| Computational and Mathematical Methods in Medicine | Comp. Math | 3 | https://www.journals.elsevier.com/journal-of-combinatorial-theory-series-a | +| Operational Research | Comp. Math | 2.97 | https://www.journals.elsevier.com/journal-of-logical-and-algebraic-methods-in-programming | +| Journal of the American Mathematical Society | Comp. Math | 2.95 | https://www.springer.com/journal/11633 | +| International Journal of Computers, Communications and Control | Comp. Math | 2.92 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=7756 | +| Computing (Vienna/New York) | Comp. Math | 2.91 | https://academic.oup.com/imaiai | +| Journal of Computational and Applied Mathematics | Comp. Math | 2.87 | https://academic.oup.com/imajna | +| Applied Numerical Mathematics | Comp. Math | 2.87 | https://www.journals.elsevier.com/information-and-computation | +| ACM Transactions on Mathematical Software | Comp. Math | 2.79 | https://www.mdpi.com/journal/computation | +| Journal of Organizational Computing and Electronic Commerce | Comp. Math | 2.76 | https://www.springer.com/journal/11390 | +| SIAM Journal of Scientific Computing | Comp. Math | 2.72 | https://www.springer.com/journal/180 | +| Information and Inference | Comp. Math | 2.69 | https://www.springer.com/journal/10915 | +| SIAM Journal on Numerical Analysis | Comp. Math | 2.69 | https://www.atlantis-press.com/journals/ijcis | +| International Journal of Computational Intelligence Systems | Comp. Math | 2.62 | https://www.springer.com/journal/10589 | +| Journal of Scientific Computing | Comp. Math | 2.62 | https://www.emerald.com/insight/publication/issn/0264-4401 | +| Computation | Comp. Math | 2.55 | https://www.journals.elsevier.com/applied-mathematics-letters | +| International Journal of Data Science and Analytics | Comp. Math | 2.52 | https://www.springer.com/journal/10044 | +| Journal of the Brazilian Society of Mechanical Sciences and Engineering | Comp. Math | 2.44 | https://www.inderscience.com/jhome.php?jcode=ijmic | +| Bayesian Analysis | Comp. Math, ML | 2.42 | https://www.ams.org/publications/journals/journalsframework/jams | +| Revista de la Real Academia de Ciencias Exactas, Fisicas y Naturales - Serie A: Matematicas | Comp. Math | 2.42 | https://journals.sagepub.com/home/act | +| Algorithms | Comp. Math | 2.36 | http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=69 | +| Journal of Strain Analysis for Engineering Design | Comp. Math | 2.33 | https://www.springer.com/journal/10 | +| Methods, Data, Analyses | Comp. Math | 2.3 | https://www.springer.com/journal/11950 | +| Journal of Applied Mathematics and Computing | Comp. Math | 2.3 | https://www.springer.com/journal/13398 | +| Journal of the European Mathematical Society | Comp. Math | 2.29 | https://www.siam.org/publications/journals/siam-journal-on-applied-mathematics-siap | +| International Journal of Intelligent Transportation Systems Research | Comp. Math | 2.27 | https://academic.oup.com/jssam | +| International Journal of Applied Mathematics and Computer Science | Comp. Math | 2.25 | https://www.global-sci.org/aamm.html | +| Applied Mathematics and Optimization | Comp. Math | 2.23 | ??? | +| Statistics and Computing | Comp. Math | 2.22 | https://www.techscience.com/journal/iasc | +| Numerische Mathematik | Comp. Math | 2.22 | https://www.springer.com/journal/12190 | +| Advances in Data Analysis and Classification | Comp. Math | 2.22 | https://www.springer.com/journal/10231 | +| Inverse Problems | Comp. Math, Signal | 2.22 | https://www.journals.elsevier.com/mechanical-systems-and-signal-processing/ | +| Measurement Science and Technology | Comp. Math | 2.21 | https://www.springer.com/journal/10255 | +| Studies in Applied Mathematics | Comp. Math | 2.2 | https://www.journals.elsevier.com/applied-mathematical-modelling | +| Optimal Control Applications and Methods | Comp. Math | 2.19 | http://acmij.az/view.php?lang=en&menu=0 | +| International Journal of Nonlinear Sciences and Numerical Simulation | Comp. Math | 2.18 | https://www.anstuocmath.ro/ | +| Journal of Computer Science and Technology | Comp. Math | 2.18 | https://www.springer.com/journal/40593 | +| Concurrency Computation Practice and Experience | Comp. Math | 2.18 | https://www.journals.elsevier.com/journal-of-complexity | +| Optimization | Comp. Math | 2.17 | https://www.springer.com/journal/11083 | +| IEEE Journal on Multiscale and Multiphysics Computational Techniques | Comp. Math | 2.15 | https://msp.org/jomms/about/journal/research.html | +| IMA Journal of Numerical Analysis | Comp. Math | 2.14 | https://dl.acm.org/journal/tocl | +| Electrical Engineering | Comp. Math | 2.12 | https://www.cambridge.org/core/journals/combinatorics-probability-and-computing | +| Software-Intensive Cyber-Physical Systems | Comp. Math | 2.11 | http://univagora.ro/jour/index.php/ijccc/ | +| Journal of Nonlinear and Variational Analysis | Comp. Math | 2.07 | https://www.springer.com/journal/10878 | +| ACM Transactions on Parallel Computing | Comp. Math | 2.05 | http://mia.ele-math.com/ | +| Smart Science | Comp. Math | 2 | https://www.cambridge.org/core/journals/numerical-mathematics-theory-methods-and-applications | +| Advances in Computational Mathematics | Comp. Math | 2 | https://www.mitpressjournals.org/loi/evco | +| Journal of Survey Statistics and Methodology | Comp. Math | 1.97 | https://www.tandfonline.com/toc/gapa20/current | +| Measurement and Control | Comp. Math | 1.97 | https://www.springer.com/journal/894 | +| Distributed Computing | Comp. Math | 1.96 | https://www.tandfonline.com/toc/hoce20/current | +| Computational Statistics and Data Analysis | Comp. Math | 1.96 | https://www.springer.com/journal/11222 | +| Journal of Molecular Modeling | Comp. Math | 1.95 | https://www.journals.elsevier.com/advances-in-applied-mathematics | +| SIAM Journal on Mathematical Analysis | Comp. Math | 1.94 | https://www.inderscience.com/jhome.php?jcode=ijcse | +| ESAIM: Mathematical Modelling and Numerical Analysis | Comp. Math | 1.94 | https://www.springer.com/journal/365 | +| SIAM Journal on Applied Mathematics | Comp. Math | 1.93 | https://dl.acm.org/journal/toms | +| Computational Optimization and Applications | Comp. Math | 1.92 | https://www.esaim-m2an.org/ | +| Bulletin of Mathematical Biology | Comp. Math | 1.91 | http://www.societyforchaostheory.org/ndpls/ | +| Mathematics of Computation | Comp. Math | 1.9 | https://www.esaim-cocv.org/ | +| East Asian Journal on Applied Mathematics | Comp. Math | 1.89 | https://www.journals.elsevier.com/operations-research-letters | +| Inverse Problems in Science and Engineering | Comp. Math | 1.88 | https://iopscience.iop.org/journal/0957-0233 | +| Analysis and Applications | Comp. Math | 1.88 | https://projecteuclid.org/euclid.ba | +| Advances in Calculus of Variations | Comp. Math | 1.84 | https://www.springer.com/journal/10623 | +| Measurement | Comp. Math | 1.84 | http://pefmath.etf.rs/ | +| ZAMM Zeitschrift fur Angewandte Mathematik und Mechanik | Comp. Math | 1.81 | https://www.tandfonline.com/loi/gitr20 | +| Advances in Fuzzy Systems | Comp. Math | 1.78 | https://www.springer.com/journal/40314 | +| Bulletin of the American Mathematical Society | Comp. Math | 1.76 | http://www.springer.com/engineering/journal/11831 | +| Engineering Computations | Comp. Math | 1.74 | https://www.journals.elsevier.com/journal-of-computer-and-system-sciences | +| Journal of Mechanics of Materials and Structures | Comp. Math | 1.74 | https://www.springer.com/journal/40315 | +| Journal of Mathematical Behavior | Comp. Math | 1.7 | https://www.journals.elsevier.com/journal-of-combinatorial-theory-series-b | +| Nonlinear Analysis, Theory, Methods and Applications | Comp. Math | 1.7 | https://www.tandfonline.com/toc/gscs20/current | +| Optimization Methods and Software | Comp. Math | 1.69 | https://www.cambridge.org/core/journals/advances-in-applied-probability | +| Communications in Contemporary Mathematics | Comp. Math | 1.66 | https://www.springer.com/journal/10114 | +| Computational Thermal Sciences | Comp. Math | 1.66 | https://www.aimsciences.org/journal/1078-0947 | +| International Journal of Computer Mathematics | Comp. Math | 1.63 | ??? | +| Research in Mathematical Sciences | Comp. Math | 1.6 | https://onlinelibrary.wiley.com/journal/14679590 | +| IEEE Pervasive Computing | Comp. Math | 1.58 | https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=12 | +| Journal of Inverse and Ill-Posed Problems | Comp. Math | 1.57 | https://www.amcs.uz.zgora.pl/ | +| Journal of Complexity | Comp. Math | 1.57 | http://www.global-sci.org/jcm/ | +| Advances in Computational Design | Comp. Math | 1.57 | https://www.journals.elsevier.com/applied-mathematics-and-computation | +| IMA Journal of Management Mathematics | Comp. Math | 1.56 | https://www.springer.com/journal/453 | +| International Journal of Computational Methods | Comp. Math | 1.54 | https://epjdatascience.springeropen.com/ | +| Computational Statistics | Comp. Math | 1.53 | https://www.degruyter.com/view/journals/jnma/jnma-overview.xml | +| Stochastic Processes and their Applications | Comp. Math | 1.51 | https://journals.sagepub.com/home/sdj | +| Discrete Optimization | Comp. Math | 1.49 | https://www.springer.com/journal/13348 | +| Constructive Approximation | Comp. Math | 1.49 | https://www.degruyter.com/view/journals/cmam/cmam-overview.xml | +| IMA Journal of Mathematical Control and Information | Comp. Math | 1.48 | http://www.informaworld.com/smpp/title~content=t713640037~db=all | +| Discrete and Continuous Dynamical Systems | Comp. Math | 1.47 | https://www.journals.elsevier.com/journal-of-mathematical-analysis-and-applications | +| Stochastic Analysis and Applications | Comp. Math | 1.46 | https://www.tandfonline.com/loi/uspp20 | +| ESAIM - Control, Optimisation and Calculus of Variations | Comp. Math | 1.45 | https://www.springer.com/journal/10444 | +| Fundamenta Informaticae | Comp. Math | 1.44 | https://www.springer.com/journal/446 | +| Designs, Codes, and Cryptography | Comp. Math | 1.44 | https://academic.oup.com/imaman | +| International Journal of Innovative Computing, Information and Control | Comp. Math | 1.43 | https://www.sciencedirect.com/journal/nonlinear-analysis | +| Journal of Combinatorial Optimization | Comp. Math | 1.42 | http://www.aimsciences.org/journal/2155-3289 | +| Applicable Analysis and Discrete Mathematics | Comp. Math | 1.4 | https://www.springer.com/journal/40430 | +| Acta Applicandae Mathematicae | Comp. Math | 1.4 | https://msp.org/camcos/2019/14-2/ | +| Lifetime Data Analysis | Comp. Math | 1.39 | http://www.aftabi.com/DIE/die.html | +| Journal of Combinatorial Theory. Series B | Comp. Math | 1.39 | https://www.journals.elsevier.com/discrete-applied-mathematics | +| Integral Transforms and Special Functions | Comp. Math | 1.39 | https://www.hindawi.com/journals/cmmm/ | +| Statistics and Public Policy | Comp. Math | 1.39 | https://www.springer.com/journal/11538 | +| Journal of Mathematical Analysis and Applications | Comp. Math | 1.38 | https://dl.acm.org/journal/topc | +| Journal of Statistical Computation and Simulation | Comp. Math | 1.38 | https://www.worldscientific.com/worldscinet/ijwmip | +| Computational Methods in Applied Mathematics | Comp. Math | 1.37 | https://www.springer.com/journal/211 | +| International Journal of Wavelets, Multiresolution and Information Processing | Comp. Math | 1.37 | https://www.combinatorics.org/ojs/index.php/eljc | +| Advances in Mathematical Physics | Comp. Math | 1.36 | https://www.global-sci.org/eajam.html | +| Differential and Integral Equations | Comp. Math | 1.36 | ??? | +| Zeitschrift fur Analysis und ihre Anwendung | Comp. Math | 1.36 | https://www.intlpress.com/site/pub/pages/journals/items/cms/_home/_main/index.php | +| Results in Mathematics | Comp. Math | 1.35 | https://www.ejgta.org/index.php/ejgta/index | +| ACM Transactions on Computational Logic | Comp. Math | 1.35 | https://www.worldscientific.com/worldscinet/ijcm | +| Transactions of the American Mathematical Society | Comp. Math | 1.34 | http://www3.interscience.wiley.com/journal/2133/home | +| International Journal of Computational Science and Engineering | Comp. Math | 1.33 | https://www.cambridge.org/core/journals/forum-of-mathematics-sigma | +| Journal of Combinatorial Theory - Series A | Comp. Math | 1.32 | https://journals.sagepub.com/home/mac | +| Algorithmica | Comp. Math | 1.31 | https://www.tandfonline.com/toc/tmes20/current | +| International Journal of Fuzzy Logic and Intelligent Systems | Comp. Math | 1.31 | https://www.worldscientific.com/worldscinet/nmnc | +| Discrete Applied Mathematics | Comp. Math | 1.31 | https://www.degruyter.com/view/journals/jiip/jiip-overview.xml | +| Mathematical and Computer Modelling of Dynamical Systems | Comp. Math | 1.29 | https://www.springer.com/journal/25 | +| Journal of Pseudo-Differential Operators and Applications | Comp. Math | 1.29 | https://academic.oup.com/imamci/ | +| Journal of Computer and System Sciences | Comp. Math | 1.29 | https://dl.acm.org/journal/toct | +| Collectanea Mathematica | Comp. Math | 1.28 | https://www.aimsciences.org/journal/1930-5311 | +| EURO Journal on Computational Optimization | Comp. Math | 1.28 | http://www.techno-press.org/?journal=acd&subpage=5 | +| Ricerche di Matematica | Comp. Math | 1.28 | https://www.springer.com/journal/11587 | +| Networks and Heterogeneous Media | Comp. Math | 1.27 | https://www.springer.com/journal/11868 | +| AStA Advances in Statistical Analysis | Comp. Math | 1.27 | https://www.aimsciences.org/journal/1930-5346 | +| Operations Research Letters | Comp. Math | 1.25 | https://www.journals.elsevier.com/discrete-optimization | +| Journal of Logical and Algebraic Methods in Programming | Comp. Math | 1.25 | https://www.mdpi.com/journal/algorithms | +| Evolution Equations and Control Theory | Comp. Math | 1.24 | https://onlinelibrary.wiley.com/journal/15320634 | +| Journal of Theoretical and Computational Acoustics | Comp. Math | 1.24 | https://www.mathos.unios.hr/mc/index.php/mc | +| Theory of Computing | Comp. Math | 1.23 | https://www.worldscientific.com/worldscinet/jtca | +| Numerical Algebra, Control and Optimization | Comp. Math | 1.22 | https://www.sciencedirect.com/journal/the-journal-of-mathematical-behavior | +| Numerical Mathematics | Comp. Math | 1.2 | https://www.siam.org/publications/journals/siam-journal-on-mathematical-analysis-sima | +| Random Structures and Algorithms | Comp. Math | 1.2 | https://www.springer.com/journal/11134 | +| Journal of Difference Equations and Applications | Comp. Math | 1.19 | http://jnva.biemdas.com/ | +| Mathematical Control and Related Fields | Comp. Math | 1.17 | https://www.springer.com/journal/30 | +| Eurasian Journal of Mathematical and Computer Applications | Comp. Math | 1.17 | http://www.informaworld.com/smpp/title~content=t713646500~db=all | +| Differential Equations and Dynamical Systems | Comp. Math | 1.14 | https://onlinelibrary.wiley.com/journal/10982418 | +| Advances in Differential Equations | Comp. Math | 1.13 | http://caim.simai.eu/index.php/caim/index | +| Advances in Applied Probability | Comp. Math | 1.13 | https://academic.oup.com/imamat | +| Nonlinear Dynamics, Psychology, and Life Sciences | Comp. Math | 1.13 | https://onlinelibrary.wiley.com/journal/14679892 | +| Annali di Matematica Pura ed Applicata | Comp. Math | 1.13 | https://www.springer.com/journal/200 | +| Forum of Mathematics, Sigma | Comp. Math | 1.12 | https://academic.oup.com/jcde | +| Journal of Statistical Planning and Inference | Comp. Math | 1.12 | https://theoryofcomputing.org/ | +| Applicable Analysis | Comp. Math | 1.11 | https://www.journals.elsevier.com/journal-of-approximation-theory | +| Advances in Applied Mathematics | Comp. Math | 1.1 | https://www.springer.com/journal/454 | +| Nonlinear Differential Equations and Applications | Comp. Math | 1.09 | https://www.degruyter.com/view/j/demo | +| International Journal of Mathematical Education in Science and Technology | Comp. Math | 1.08 | https://www.springer.com/journal/224 | +| Journal of Approximation Theory | Comp. Math | 1.08 | https://www.aimsciences.org/journal/2156-8472 | +| Journal of Time Series Analysis | Comp. Math | 1.07 | https://journals.math.tku.edu.tw/index.php/TKJM | +| Journal of Algorithms and Computational Technology | Comp. Math | 1.07 | https://link.springer.com/journal/13675 | +| Communications in Mathematical Biology and Neuroscience | Comp. Math | 1.05 | https://www.tandfonline.com/toc/gipe20/current | +| Communications in Mathematical Sciences | Comp. Math | 1.05 | https://www.journals.elsevier.com/stochastic-processes-and-their-applications | +| New Mathematics and Natural Computation | Comp. Math | 1.04 | https://www.springer.com/education+%26+language/learning+%26+instruction/journal/10758 | +| International Journal of Grid and Utility Computing | Comp. Math | 1.04 | https://academic.oup.com/qjmam | +| Quarterly of Applied Mathematics | Comp. Math | 1.03 | https://www.aimsciences.org/journal/1556-1801 | +| Advances in Applied Mathematics and Mechanics | Comp. Math | 1.03 | https://www.worldscientific.com/worldscinet/ccm | +| Quarterly Journal of Mechanics and Applied Mathematics | Comp. Math | 1.02 | https://www.ams.org/publications/journals/journalsframework/proc | +| Information and Computation | Comp. Math | 1.01 | https://www.iospress.nl/journal/fundamenta-informaticae/ | +| Journal of Symbolic Computation | Comp. Math | 1.01 | https://www.journals.elsevier.com/journal-of-computational-and-applied-mathematics | +| Analele Stiintifice ale Universitatii Ovidius Constanta, Seria Matematica | Comp. Math | 1.01 | https://www.hindawi.com/journals/amp/ | +| Aequationes Mathematicae | Comp. Math | 1.01 | https://www.degruyter.com/view/j/form | +| Advances in Mathematics of Communications | Comp. Math | 1.01 | https://www.degruyter.com/view/j/agms | +| Computational Methods and Function Theory | Comp. Math | 1.01 | http://ejmca.enu.kz/ | +| Communications in Applied Mathematics and Computational Science | Comp. Math | 1 | https://www.ams.org/publications/journals/journalsframework/qam | +| Analysis and Geometry in Metric Spaces | Comp. Math | 1 | https://ieee-jmmct.org/ | +| Mathematical Inequalities and Applications | Comp. Math | 1 | https://www.inderscience.com/jhome.php?jcode=ijguc | +| Queueing Systems | Comp. Math | 1 | https://www.springer.com/journal/11786 | +| IMA Journal of Applied Mathematics | Comp. Math | 0.99 | http://www.aftabi.com/ADE/ade.html | +| Journal of Computational Mathematics | Comp. Math | 0.98 | https://www.journals.elsevier.com/journal-of-statistical-planning-and-inference | +| Tamkang Journal of Mathematics | Comp. Math | 0.98 | https://www.springer.com/journal/10182 | +| Forum Mathematicum | Comp. Math | 0.97 | http://www.springer.com/engineering/electronics/journal/202 | +| Proceedings of the American Mathematical Society | Comp. Math | 0.96 | https://www.springer.com/journal/12591 | +| Vestnik Sankt-Peterburgskogo Universiteta, Prikladnaya Matematika, Informatika, Protsessy Upravleniya | Comp. Math | 0.95 | https://mda.gesis.org/index.php/mda/index | +| Mathematical Communications | Comp. Math | 0.95 | https://onlinelibrary.wiley.com/journal/15214001 | +| European Journal of Applied Mathematics | Comp. Math | 0.94 | https://www.tandfonline.com/toc/lsaa20/current | +| Qualitative Theory of Dynamical Systems | Comp. Math | 0.92 | https://www.springer.com/journal/10985 | +| European Journal of Combinatorics | Comp. Math | 0.92 | https://www.tandfonline.com/toc/goms20/current | +| Communications in Applied and Industrial Mathematics | Comp. Math | 0.92 | https://www.cambridge.org/core/journals/european-journal-of-applied-mathematics | +| Discrete and Computational Geometry | Comp. Math | 0.89 | https://www.journals.elsevier.com/european-journal-of-combinatorics | +| ACM Transactions on Computation Theory | Comp. Math | 0.88 | https://www.journals.elsevier.com/computers-and-mathematics-with-applications | +| Combinatorics Probability and Computing | Comp. Math | 0.87 | https://www.tandfonline.com/toc/hmes20/current | +| Computing and Informatics | Comp. Math | 0.87 | http://www.compama.co.usb.ve/ | +| International Journal of Computing Science and Mathematics | Comp. Math | 0.86 | http://www.hindawi.com/journals/afs/ | +| Theory of Computing Systems | Comp. Math | 0.84 | https://www.ems-ph.org/journals/journal.php?jrn=zaa | +| Bulletin of the South Ural State University, Series: Mathematical Modelling, Programming and Computer Software | Comp. Math | 0.83 | http://www.apmath.spbu.ru/ru/resource/vestnik/ | +| Applied Mathematics | Comp. Math | 0.8 | https://www.degruyter.com/view/j/jaa?lang=en | +| International Journal of Modelling, Identification and Control | Comp. Math | 0.8 | https://www.springer.com/journal/10440 | +| Acta Mathematica Sinica, English Series | Comp. Math | 0.8 | https://www.springer.com/engineering/electronics/journal/13177 | +| Applied Mathematics E - Notes | Comp. Math | 0.79 | https://mmp.susu.ru/page/en/greet | +| Bulletin of Computational Applied Mathematics | Comp. Math | 0.78 | http://www.math.nthu.edu.tw/~amen/ | +| Order | Comp. Math | 0.76 | https://www.begellhouse.com/journals/computational-thermal-sciences.html | +| Communications in Mathematics and Statistics | Comp. Math | 0.73 | https://www.journals.elsevier.com/applied-numerical-mathematics/ | +| Applicable Algebra in Engineering, Communications and Computing | Comp. Math | 0.72 | ??? | +| Journal of Modern Dynamics | Comp. Math | 0.68 | https://www.springer.com/journal/12346 | +| Journal of Applied Analysis | Comp. Math | 0.67 | http://www.cai.sk/ojs/index.php/cai | +| Electronic Journal of Graph Theory and Applications | Comp. Math | 0.66 | https://mcfns.net/index.php/Journal | +| Electronic Journal of Combinatorics | Comp. Math | 0.63 | ??? | +| Acta Mathematicae Applicatae Sinica | Comp. Math | 0.62 | https://www.degruyter.com/view/journals/acv/acv-overview.xml | +| Mathematics in Computer Science | Comp. Math | 0.54 | https://www.springer.com/journal/11634 | +| Dependence Modeling | Comp. Math | 0.52 | https://www.aimsciences.org/journal/A0000-0000 | +| Journal of Computational Methods in Sciences and Engineering | Comp. Math | 0.48 | https://www.springer.com/journal/11766 | +| Mathematical and Computational Forestry and Natural-Resource Sciences | Comp. Math | 0.47 | https://www.degruyter.com/view/journals/ijnsns/ijnsns-overview.xml | +| Journal of Applied Mathematics and Informatics | Comp. Math | 0.47 | https://www.iospress.nl/journal/journal-of-computational-methods-in-sciences-and-engineering/ | diff --git a/_i18n/en/education.md b/_i18n/en/education.md index 3c912ce2..143854aa 100644 --- a/_i18n/en/education.md +++ b/_i18n/en/education.md @@ -1,104 +1,100 @@ -# Расписание - -## Осенний семестр, 2025 - -### Занятия онлайн -- бакалавры [m1p.org/go_zoom](https://m1p.org/go_zoom) -- магистры [m1p.org/go_zoom2](https://m1p.org/go_zoom2) -- канал [youtube.com/@MachineLearningPhystech](https://www.youtube.com/@MachineLearningPhystech) - -### Расписание занятий - -#### 4 курс, 7 семестр - вторник - -| Время | Предмет | Преподаватели | Форма отчетности | Зачетные единицы | -|---|---|---|---|---| -| 10:30-12:00 | [Методы глубокого обучения: лекция](/ru/course/deep_learning/index.html) | [Филатов А.В.](/ru/people/filatov_av/index.html), [Яковлев К.Д.](/ru/people/yakovlev_kd) | Дифф. зачет | 2 | -| 12:10-13:40 | [Методы глубокого обучения: семинар](/ru/course/deep_learning/index.html) | [Филатов А.В.](/ru/people/filatov_av/index.html), [Яковлев К.Д.](/ru/people/yakovlev_kd)| | | -| 14:30-16:00 | [Байесовский выбор моделей](/ru/course/bayesian_model_selection/index.html) | [Адуенко А.А.](/ru/people/aduenko_aa/index.html), [Яковлев К.Д.](/ru/people/yakovlev_kd) | Дифф. зачет | 1 | -| 16:10-17:40 | [Математические методы прогнозирования](/ru/course/forecasting_methods/index.html) | [Тихонов Д.М.](/ru/people/tikhonov_dm) | Дифф. зачет | 1 | - -#### 5 курс, 9 семестр - вторник - -| Время | Предмет | Преподаватели | Форма отчетности | Зачетные единицы | -|---|---|---|---|---| -| 14:30-16:00 | [Байесовское мультимоделирование](/ru/course/bayesian_multimodeling/index.html) | [Бахтеев О.Ю.](/ru/people/bakhteev_oy/index.html)| Дифф. зачет | 2 | -| 16:10-17:40 | [Создание интеллектуальных систем](/ru/course/rnd_in_ai/index.html) | [Грабовой А.В.](/ru/people/grabovoy_av/index.html) | Дифф. зачет | 2 | -| 18:00-19:30 | [Порождающие модели машинного обучения: лекция](/ru/course/deep_generative_models/index.html) | [Исаченко Р.В.](/ru/people/isachenko_rv/index.html), Морозов М. | Экзамен | 3 | -| 19:30-21:00 | [Порождающие модели машинного обучения: семинар](/ru/course/deep_generative_models/index.html) | [Исаченко Р.В.](/ru/people/isachenko_rv/index.html), Морозов М. | | | - -#### 6 курс, 11 семестр - четверг - -| Время | Предмет | Преподаватели | Форма отчетности | Зачетные единицы | -|---|---|---|---|---| -| 10:30-12:00 | [Обработка сигналов](/ru/course/signal_processing/index.html) | [Северилов П.А.](/ru/people/severilov_pa/index.html) | Экзамен | 3 | -| 12:10-13:40 | [Интеллектуальный анализ данных](/ru/course/intellectual_data_analysis/index.html) | [Стрижов В.В.](/ru/people/strijov_vv/index.html), [Бахтеев О.Ю.](/ru/people/bakhteev_oy/index.html) | Зачет | 2 | -| 14:30-16:00 | [Вероятностные тематические модели](/ru/course/probabilistic_topic_models/index.html) | [Воронцов К.В.](/ru/people/vorontsov_kv/index.html) | Дифф. зачет | 2 | - -### Ключевые даты -- **2 сентября** - завершение приема заявок на научную стипендию -- **6 сентября** - начало занятий на кафедре -- **11,12 сентября** - научная ориентация и обсуждение требований к НИР -- **5 октября** - презентация кафедры для 3 курса (вечером, офлайн) -- **1 ноября** - собеседование на кафедру, начало в 15:00 - -- **15-21 декабря** - зачетная неделя для 3–6 курсов -- **2-15 декабря** - конференция ММРО -- **21 декабря** - зачёт по НИР для 3–6 курсов и аспирантов -- **17 января** - гос. экзамен 6 курса - -## Весенний семестр, 2026 - -#### 3 курс, 6 семестр – четверг - -| Время | Предмет | Преподаватели | Форма отчетности | Зачетные единицы | -|---|---|---|---|---| -| 12:10-13:40 | [Введение в машинное обучение](/ru/course/introduction_machine_learning/index.html) | [Грабовой А.В.](/ru/people/grabovoy_av/index.html), [Воронцов К.В.](/ru/people/vorontsov_kv/index.html) | Дифф. зачет | 1 | -| 14:30-16:00 | [Практикум по программированию на языке Питон](https://github.com/MelLain/mipt-python) | [Апишев М.А.](/people/apishev_ma/index.html) | Зачет | 1 | -| 16:10-17:40 | [Создание интеллектуальных систем](/ru/course/rnd_in_ai/index.html) | Стрижов В.В., [Грабовой А.В.](/ru/people/grabovoy_av/index.html) | Зачет | 1 | -| 17:50-19:20 | [Автоматизация научных исследований (Моя первая научная статья)](http://m1p.org) | Стрижов В.В., [Бахтеев О.Ю.](/ru/people/bakhteev_oy/index.html), [Грабовой А.В.](/ru/people/grabovoy_av/index.html) | Дифф. зачет | 1 | - -#### 4 курс, 8 семестр – вторник - -| Время | Предмет | Преподаватели | Форма отчетности | Зачетные единицы | -|---|---|---|---|---| -| 10:30-12:00 | [Рекомендательные системы](/ru/course/recommender_systems/index.html) | [Гришанов А.В.](/ru/people/grishanov_av/index.html), [Володкевич А.А.](/ru/people/volodkevich_aa/index.html) | Дифф. зачет | 2 | -| 12:10-13:40 | [Математические методы прогнозирования](/ru/course/forecasting_methods/index.html) | [Тихонов Д.М.](/ru/people/tikhonov_dm) | Дифф. зачет | 3 | -| 14:30-16:00 | [Байесовский выбор моделей](/ru/course/bayesian_model_selection/index.html) | [Адуенко А.А.](/ru/people/aduenko_aa/index.html) | Экзамен | 2 | -| 16:10-17:40 | [Планирование проектов по созданию программного обеспечения](/ru/course/software_engineering_data_analysis/index.html) | [Хританков А.С.](/ru/people/khritankov_as/index.html) | Дифф. зачет | 1 | - -#### 5 курс, 10 семестр – вторник - -| Время | Предмет | Преподаватели | Форма отчетности | Зачетные единицы | -|---|---|---|---|---| -| 10:30-12:00 | | | | | -| 12:10-13:40 | [Биоинформатика](/ru/course/bioinformatics/index.html) | [Торшин И.Ю.](/ru/people/torshin_iy/index.html) | Дифф. зачет | 1 | -| 14:30-16:00 | [Создание интеллектуальных систем](/ru/course/rnd_in_ai/index.html) | [Грабовой А.А.](/ru/people/grabovoy_av/index.html) | Экзамен | 2 | -| 16:10-17:40 | [Планирование проектов по созданию программного обеспечения](/ru/course/software_engineering_data_analysis/index.html) | [Хританков А.С.](/ru/people/khritankov_as/index.html) | Дифф. зачет | 1 | -| 17:50-19:20 | [Байесовское мультимоделирование](/ru/course/bayesian_multimodeling/index.html) | [Бахтеев О.Ю.](/ru/people/bakhteev_oy/index.html) | Экзамен | 2 | - - - -### Ключевые даты - - - -- **9 февраля** - начало занятий -- **9 февраля** - завершение приема заявок на научную стипендию -- **4 марта** - понедельник 18:30 рассказ о кафедре для студентов второго курса, офлайн -- **10 марта** - завершение приема работ на конференцию МФТИ -- **4 апреля** - 13:00 конференция и обсуждение ВКР 4 и 6 курсов -- **18-24 мая** - зачетная неделя для 3–6 курсов -- **13 мая** - 17:00 (суббота) зачёт по НИР для 3–6 курсов и аспирантов -- **2 июня** - кандидатский экзамен у аспирантов -- **6 июня** - 10:00 предзащита 6 курса -- **13 июня** - ГИА у выпускающихся аспирантов -- **13 июня** - 10:00 предзащита 4 курса -- **17 июня** - в 13:00 (среда) защита 6 курса, очно ВЦ 355 -- **17 июня** - научный доклад у выпускающихся аспирантов -- **24 июня** - в 13:00 (среда) защита 4 курса, очно ВЦ 355 - -## Документы и ссылки -- График учебного процесса: [ссылка]([https://mipt.ru/about/departments/uchebniy/schedule/study/](https://mipt.ru/upload/%D0%A3%D1%87%D0%B5%D0%B1%D0%BD%D0%BE%D0%B5%20%D1%83%D0%BF%D1%80%D0%B0%D0%B2%D0%BB%D0%B5%D0%BD%D0%B8%D0%B5/%D0%A0%D0%B0%D1%81%D0%BF%D0%B8%D1%81%D0%B0%D0%BD%D0%B8%D0%B5%20%D1%81%D0%B5%D1%81%D1%81%D0%B8%D0%B8/%D0%9B%D0%95%D0%A2%D0%9E%202023-2024/%D0%93%D1%80%D0%B0%D1%84%D0%B8%D0%BA%20%D1%83%D1%87%D0%B5%D0%B1%D0%BD%D0%BE%D0%B3%D0%BE%20%D0%BF%D1%80%D0%BE%D1%86%D0%B5%D1%81%D1%81%D0%B0%20%D0%BD%D0%B0%20%D1%81%D0%B0%D0%B9%D1%82.docx.pdf) -- Шаблон отчета по НИР: [ссылка](https://docs.google.com/document/d/1XsYWC7isbiums9jqjzddHIkDjvxqKNvf/edit?usp=sharing). -- Программа государственного экзамена для 6 курса: [ссылка](https://docs.google.com/document/d/1KkePnIg2BOf_LHBLBbgRL0W4gqKtt1W0OhJSg43lR_Y/edit?usp=sharing). +## Schedule + +**Online Classes:** + +- Bachelor's: [m1p.org/go_zoom](https://m1p.org/go_zoom) +- Master's: [m1p.org/go_zoom2](https://m1p.org/go_zoom2) +- YouTube: [youtube.com/@MachineLearningPhystech](https://www.youtube.com/@MachineLearningPhystech) + +**Documents and Links:** + +- Institute Schedule: [link](https://mipt.ru/upload/%D0%A3%D1%87%D0%B5%D0%B1%D0%BD%D0%BE%D0%B5%20%D1%83%D0%BF%D1%80%D0%B0%D0%B2%D0%BB%D0%B5%D0%BD%D0%B8%D0%B5/%D0%A0%D0%B0%D1%81%D0%BF%D0%B8%D1%81%D0%B0%D0%BD%D0%B8%D0%B5%20%D1%81%D0%B5%D1%81%D1%81%D0%B8%D0%B8/%D0%9B%D0%95%D0%A2%D0%9E%202023-2024/%D0%93%D1%80%D0%B0%D1%84%D0%B8%D0%BA%20%D1%83%D1%87%D0%B5%D0%B1%D0%BD%D0%BE%D0%B3%D0%BE%20%D0%BF%D1%80%D0%BE%D1%86%D0%B5%D1%81%D1%81%D0%B0%20%D0%BD%D0%B0%20%D1%81%D0%B0%D0%B9%D1%82.docx.pdf) +- Research Report Template: [link](https://docs.google.com/document/d/1XsYWC7isbiums9jqjzddHIkDjvxqKNvf/edit?usp=sharing) +- State Exam Program for 6th Year: [link](https://docs.google.com/document/d/1KkePnIg2BOf_LHBLBbgRL0W4gqKtt1W0OhJSg43lR_Y/edit?usp=sharing) + +### Fall 2025 + +#### Key Dates + +- **September 2:** Deadline for [scholarship]({{ site.baseurl }}/materials/scholarship) applications +- **September 6:** Start of classes at the department +- **September 11-12:** Organizational meeting +- **October 23:** Department presentation for 3rd year students +- **November 1:** Interview for 3rd year students applying to the department +- **December 15-21:** Exam week for 3rd to 6th year students +- **December 21:** ❗️ Credit on Research (be ready with paper/code/slides) +- **January 17:** State exam for 6th year students + +#### 4th year, 7th semester (Tuesday) + +| Time | Course | Instructors | Assessment Type | Credits | +| ----------- | --------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------- | ------- | +| 10:30-12:00 | [Deep Learning: Lecture]({{ site.baseurl }}/course/deep_learning) | [Eduard Vladimirov]({{ site.baseurl }}/people/vladimirov_ea), [Daniil Dorin]({{ site.baseurl }}/people/dorin_dd), [Nikita Kiselev]({{ site.baseurl }}/people/kiselev_ns), [Sergey Firsov]({{ site.baseurl }}/people/firsov_sa), [Vadim Kasiuk]({{ site.baseurl }}/people/kasiuk_va) | Differentiated credit | 2 | +| 12:10-13:40 | [Deep Learning: Seminar]({{ site.baseurl }}/course/deep_learning) | [Eduard Vladimirov]({{ site.baseurl }}/people/vladimirov_ea), [Daniil Dorin]({{ site.baseurl }}/people/dorin_dd), [Nikita Kiselev]({{ site.baseurl }}/people/kiselev_ns), [Sergey Firsov]({{ site.baseurl }}/people/firsov_sa), [Vadim Kasiuk]({{ site.baseurl }}/people/kasiuk_va) | | | +| 14:30-16:00 | [Bayesian Model Selection]({{ site.baseurl }}/course/bayesian_model_selection) | [Alexander Aduenko]({{ site.baseurl }}/people/aduenko_aa), [Konstantin Yakovlev]({{ site.baseurl }}/people/yakovlev_kd) | Differentiated credit | 1 | +| 16:10-17:40 | [Mathematical Forecasting Methods]({{ site.baseurl }}/course/forecasting_methods) | [Denis Tikhonov]({{ site.baseurl }}/people/tikhonov_dm), [Sviatoslav Panchenko]({{ site.baseurl }}/people/panchenko_sk) | Differentiated credit | 1 | + +#### 5th year, 9th semester (Tuesday) + +| Time | Course | Instructors | Assessment Type | Credits | +| ----------- | ----------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- | --------------------- | ------- | +| 14:30-16:00 | [Bayesian Multimodeling]({{ site.baseurl }}/course/bayesian_multimodeling) | [Oleg Bakhteev]({{ site.baseurl }}/people/bakhteev_oy) | Differentiated credit | 2 | +| 16:10-17:40 | [Creation of Intelligent Systems]({{ site.baseurl }}/course/rnd_in_ai) | [Andrey Grabovoy]({{ site.baseurl }}/people/grabovoy_av) | Differentiated credit | 2 | +| 18:00-19:30 | [Deep Generative Models: Lecture]({{ site.baseurl }}/course/deep_generative_models) | [Roman Isachenko]({{ site.baseurl }}/people/isachenko_rv), [Matvey Morozov]({{ site.baseurl }}/people/morozov_ma) | Exam | 3 | +| 19:30-21:00 | [Deep Generative Models: Seminar]({{ site.baseurl }}/course/deep_generative_models) | [Roman Isachenko]({{ site.baseurl }}/people/isachenko_rv), [Matvey Morozov]({{ site.baseurl }}/people/morozov_ma) | | | + +#### 6th year, 11th semester (Thursday) + +| Time | Course | Instructors | Assessment Type | Credits | +| ----------- | ---------------------------------------------------------------------------------- | -------------------------------------------------------------- | --------------------- | ------- | +| 10:30-12:00 | [Functional Data Analysis]({{ site.baseurl }}/course/functional_data_analysis) | [Vadim Strijov]({{ site.baseurl }}/people/strijov_vv) | Exam | 3 | +| 12:10-13:40 | [Intellectual Data Analysis]({{ site.baseurl }}/course/intellectual_data_analysis) | [Vadim Strijov]({{ site.baseurl }}/people/strijov_vv) | Credit | 2 | +| 14:30-16:00 | [Probabilistic Topic Models]({{ site.baseurl }}/course/probabilistic_topic_models) | [Konstantin Vorontsov]({{ site.baseurl }}/people/vorontsov_kv) | Differentiated credit | 2 | + +
+ +### Spring 2025 + +#### Key Dates + +- **February 6:** Start of classes at the department +- **February 9:** Deadline for [scholarship]({{ site.baseurl }}/materials/scholarship) applications +- **March 4:** Monday 18:30 presentation about the department for second-year students, offline +- **March 10:** Deadline for submissions to the MIPT conference +- **April 4:** 13:00 conference and discussion of theses for 4th and 6th year students +- **May 18-24:** Exam week for 3rd to 6th year students +- **May 13:** 17:00 (Saturday) Credit on research work for 3rd-6th year and postgraduate students +- **June 2:** PhD qualifying exam for postgraduate students +- **June 6:** 10:00 predefense for 6th year students +- **June 13:** State final attestation for graduating postgraduate students +- **June 13:** 10:00 predefense for 4th year students +- **June 17:** 13:00 (Wednesday) defense for 6th year students, offline 355 room +- **June 17:** Scientific report for graduating postgraduate students +- **June 24:** 13:00 (Wednesday) defense for 4th year students, offline 355 room + +#### 3rd year, 6th semester – Thursday + +| Time | Course | Instructors | Assessment Type | Credits | +| ----------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------- | ------- | +| 12:10-13:40 | [Introduction to Machine Learning]({{ site.baseurl }}/course/introduction_machine_learning) | [Andrey Grabovoy]({{ site.baseurl }}/people/grabovoy_av), [Konstantin Vorontsov]({{ site.baseurl }}/people/vorontsov_kv) | Differentiated credit | 1 | +| 14:30-16:00 | [Programming Practicum in Python](https://github.com/MelLain/mipt-python) | [Murat Apishev]({{ site.baseurl }}/people/apishev_ma) | Credit | 1 | +| 16:10-17:40 | [Creation of Intelligent Systems]({{ site.baseurl }}/course/rnd_in_ai) | [Andrey Grabovoy]({{ site.baseurl }}/people/grabovoy_av), [Vadim Strijov]({{ site.baseurl }}/people/strijov_vv) | Credit | 1 | +| 17:50-19:20 | [My First Scientific Paper](http://m1p.org) | [Andrey Grabovoy]({{ site.baseurl }}/people/grabovoy_av), [Oleg Bakhteev]({{ site.baseurl }}/people/bakhteev_oy), [Vadim Strijov]({{ site.baseurl }}/people/strijov_vv) | Differentiated credit | 1 | + +#### 4th year, 8th semester – Tuesday + +| Time | Course | Instructors | Assessment Type | Credits | +| ----------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | --------------------- | ------- | +| 10:30-12:00 | [Recommender Systems]({{ site.baseurl }}/course/recommender_systems) | [Alexey Grishanov]({{ site.baseurl }}/people/grishanov_av), [Anna Volodkevich]({{ site.baseurl }}/people/volodkevich_aa) | Differentiated credit | 2 | +| 12:10-13:40 | [Mathematical Forecasting Methods]({{ site.baseurl }}/course/forecasting_methods) | [Denis Tikhonov]({{ site.baseurl }}/people/tikhonov_dm), [Sviatoslav Panchenko]({{ site.baseurl }}/people/panchenko_sk) | Differentiated credit | 3 | +| 14:30-16:00 | [Bayesian Model Selection]({{ site.baseurl }}/course/bayesian_model_selection) | [Alexander Aduenko]({{ site.baseurl }}/people/aduenko_aa), [Konstantin Yakovlev]({{ site.baseurl }}/people/yakovlev_kd) | Exam | 2 | +| 16:10-17:40 | [Software Engineering for Machine Learning]({{ site.baseurl }}/course/software_engineering_data_analysis) | [Anton Khritankov]({{ site.baseurl }}/people/khritankov_as) | Differentiated credit | 1 | + +#### 5th year, 10th semester – Tuesday + +| Time | Course | Instructors | Assessment Type | Credits | +| ----------- | --------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- | --------------------- | ------- | +| 12:10-13:40 | [Bioinformatics]({{ site.baseurl }}/course/bioinformatics) | [Ivan Torshin]({{ site.baseurl }}/people/torshin_iy) | Differentiated credit | 1 | +| 14:30-16:00 | [Creation of Intelligent Systems]({{ site.baseurl }}/course/rnd_in_ai) | [Andrey Grabovoy]({{ site.baseurl }}/people/grabovoy_av) | Exam | 2 | +| 16:10-17:40 | [Software Engineering for Machine Learning]({{ site.baseurl }}/course/software_engineering_data_analysis) | [Anton Khritankov]({{ site.baseurl }}/people/khritankov_as) | Differentiated credit | 1 | +| 17:50-19:20 | [Bayesian Multimodeling]({{ site.baseurl }}/course/bayesian_multimodeling) | [Oleg Bakhteev]({{ site.baseurl }}/people/bakhteev_oy) | Exam | 2 | diff --git a/_i18n/en/index.md b/_i18n/en/index.md index f09c6eb2..c9e96b66 100644 --- a/_i18n/en/index.md +++ b/_i18n/en/index.md @@ -1,16 +1,236 @@ -### [Class timetable](/ru/education/) - -[Department of Intelligent Systems](/ru/about/) graduates bachelors and masters in the field of study "Applied Mathematics and physics". - -### Announcements and Information -- [Admission](/admission/) -- [For external students](/admission/) -- [Courses](/course/) and [teachers](/people/) -- [Scientific and educational projects](https://m1p.org) -- **Telegram** for [students](https://t.me/IS_MIPT) and [graduates](https://t.me/+BpMhAW-gWlM5OThi) -- **Youtube** [Machine Learning – Intelligent Sytstems](https://www.youtube.com/@MachineLearningIS) -- **Rutube** [Machine learning – Intelligent Systems](https://rutube.ru/channel/40144363) - -**Online channels:** -* bachelors [m1p.org/go_zoom](https://m1p.org/go_zoom) -* masters [m1p.org/go_zoom2](https://m1p.org/go_zoom2) +
+
+
+
+

Department of

+

Intelligent Systems

+

+ We train specialists in applied mathematics and physics — from bachelor's to PhD. Our research spans machine learning theory, intelligent systems, and real-world applications. Based at the Dorodnicyn Computing Centre of RAS, we unite academic excellence with industry collaboration. +

+
+ {% if site.github %} + + {% endif %} + {% if site.mail %} + + {% endif %} + {% if site.telegram %} + + {% endif %} + {% if site.youtube %} + + {% endif %} +
+
+
+ + +
+

News

+
+
+
+ {% if site.posts and site.posts.size > 0 %} + {% assign news_sorted = site.posts | where: "lang", "en" | sort: 'date' | reverse %} + {% for post in news_sorted limit:10 %} + +
+ {% if post.important %} + IMPORTANT + {% endif %} +
+

{{ post.title }}

+

{{ post.date | date: "%d.%m.%Y" }}

+

{{ post.excerpt }}

+ + {% endfor %} + {% else %} + No news available + {% endif %} +
+
+
+
+ + +
+

About

+
+

The Department of Intelligent Systems at the Phystech School of Applied Mathematics and Informatics (MIPT) is a leading center for education and research in applied mathematics, data science, and artificial intelligence. The department offers bachelor’s and master’s programs in “Applied Mathematics and Physics” with specializations in Data Science, Intelligent Systems Design, and Machine Learning.

+

Founded by academician Konstantin Vladimirovich Rudakov and developed within the scientific school of academician Yuri Ivanovich Zhuravlev, the department is based at the Computing Center of the Russian Academy of Sciences. Our faculty includes renowned professors, young scientists, and industry experts, with an average age of 35 years.

+

Research at the department covers machine learning, multivariate statistics, deep learning, model selection, generative neural networks, and analysis of complex data. Applied projects include text and image analysis, biomedical signal processing, and brain-computer interfaces. The department actively collaborates with international universities, research centers, and high-tech companies, offering students unique opportunities for internships, double degrees, and joint research.

+

We value openness, innovation, and continuous improvement, supporting students with scholarships and personal mentorship. Join us to study, research, and innovate in the field of intelligent systems!

+
+
+ + +
+
+
+

2003

+

year the department was founded

+
+
+

>50%

+

of graduates defended PhD dissertations

+
+
+

<35

+

years average age of courses instructors

+
+
+

170+

+

open source projects on GitHub

+
+
+

every
semester

+

students submit research reports: paper-code-presentation

+
+
+

NeurIPS,
ICML, ICLR,
AISTATS

+

top-tier conferences publish our research

+
+
+
+ + +
+

Personalities

+

+ We are proud of our founders and lecturers, who have made significant contributions to the field of intelligent systems. Their work has paved the way for advancements in artificial intelligence and machine learning. +

+ {% assign featured_people = "zhuravlyov_yv,rudakov_kv,vorontsov_kv,strijov_vv" | split: "," %} +
+ {% for person_id in featured_people %} + {% for profile in site.people %} + {% assign profile_id = profile.id | split: "/" | last %} + {% if profile_id == person_id %} +
+

+ {% if profile.avatar %} + + {% else %} + + {% endif %} + {% t people.{{ profile_id }} %} +

+
+ {% endif %} + {% endfor %} + {% endfor %} +
+
+ + +
+

Courses

+

+ We offer a range of courses in applied mathematics, data science, and machine learning for both bachelor's and master's students. Our curriculum is designed to provide a strong theoretical foundation along with practical skills needed in the industry. +

+ {% for type in site.global.course.types %} + {% if type == 'bachelor' or type == 'master' %} +
+

{% t site.global.course.types.{{ type }} %}

+
+
+ {% for course in site.course %} + {% if course.type contains type %} + +
+

+ {% t courses.{{ course.id | split: "/" | last }} %} +

+
+ + {% endif %} + {% endfor %} +
+ {% endif %} + {% endfor %} +
+ + +
+ +
+ + +
+

Research

+
+

+ We openly publish research results and invite collaboration with students, researchers, and industry partners. +

+
+
+ Scientific Research +

+ Our department conducts fundamental and applied research in machine learning, data analysis, artificial intelligence, and related fields. + Results are published in open access and presented at international conferences. We welcome joint projects and new ideas! +

+

+ Focus areas: ML algorithms, AI research, data science +

+
+
+ Theses +

+ Students participate in real research, prepare diploma theses, and publish their results. + We support open publication of code and articles, and invite everyone to collaborate on thesis topics and research projects. +

+

+ Student work: Bachelor's & Master's theses, publications +

+
+
+ Scholarships +

+ We support the research of our students by awarding several scholarships each semester. + The scientific academic scholarship named after K.V. Rudakov is awarded to undergraduate and graduate students for academic and research excellence. + Sponsored by Forecsys Group. +

+
+
+
Internships
+

+ Since the beginning, the department has been actively cooperating with the base companies of the Forecsys Group of Companies and participates in joint projects with leading tech companies. +

+
+

Forecsys

+

Antiplagiat

+

Yandex

+

SBER

+
+
+
+
+
+ + +
+

Our Life

+

+ Here we share some moments from our department's life, including events, student activities, and memorable experiences. +

+ +
diff --git a/_i18n/en/nir.md b/_i18n/en/nir.md index 18eda1c3..9e86e46d 100644 --- a/_i18n/en/nir.md +++ b/_i18n/en/nir.md @@ -1,460 +1,457 @@ -### 2025 SPRING - -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -|Konstantin Yakovlev | 1 | Tensor Methods in Federated Learning| [Gasnikov A.V.](https://scholar.google.com/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Publication 1](https://neurips.cc/virtual/2024/poster/93240), [Publication 2](https://arxiv.org/abs/2502.13662) | -|Grigoriy Ksenofontov | 1 | Discrete Schrödinger Bridges | [Korotin A.A.](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Publication](https://arxiv.org/abs/2502.01416), [Code](https://github.com/gregkseno/csbm), [Slides](https://www.overleaf.com/read/wqycyqmzwjpw#b5787d) | - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Nikita Kornilov | 2 | Optimal Flow Matching: Learning Straight Trajectories in Just One Step | Gasnikov A.V. | [Publication](https://proceedings.neurips.cc/paper_files/paper/2024/file/bc8f76d9caadd48f77025b1c889d2e2d-Paper-Conference.pdf), [Slides](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/slides/Kornilov%20slides%20Research.pdf), [Paper](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/paper/Kornilov_Nikita_Thesis.pdf), [Code](https://github.com/intsystems/Kornilov_2024_NIR/tree/master)| -| Galina Boeva | 2 | Efficient aggregation by labels for the problem of event sequences | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Publication](https://ebooks.iospress.nl/volumearticle/70171?_gl=1*1kzsn7p*_up*MQ..*_ga*MTE2NzcyNzQzLjE3MzM4MjMzNDE.*_ga_6N3Q0141SM*MTczMzgyMzM0MS4xLjAuMTczMzgyMzM0MS4wLjAuMA..), [Slides](https://github.com/Gaechka777/NIR24_25/blob/master/slides/slides_nir_12sem.pdf), [Paper](https://arxiv.org/abs/2303.00280), [Code](https://github.com/intsystems/Boeva-MS-Thesis)| -| Vladimirov Eduard | 2 | Generative causal inference for Brain-Computer Interfaces | Strijov V. V. | [Paper](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/paper/Vladimirov2024GenerativeCIPaper.pdf), [Slides](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/slides/Vladimirov2024GenerativeCISlides.pdf), [Code](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master/code)| -| Bair Mikhailov | 2 | Development of Machine Learning Methods for Radiology in Brain Evolution Research| [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Paper](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/paper/main.pdf), [Slides](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/slides/slides.pdf), [Code](https://github.com/intsystems/Mikhailov-MS-Thesis)| -| Arina Chumachenko | 2 | Preventing Overfitting in Subject-Driven Text-to-Image Diffusion: Regularization of Embedding and Attention Maps | [Oseledets I.V.](https://faculty.skoltech.ru/people/ivanoseledets) | [Paper](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/paper/MSc_Thesis_Chumachenko.pdf), [Slides](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/slides/MSc_Defense_Chumachenko.pdf), [Code](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis) | -| German Gritsai | 2 | Verification of artificially generated text fragments | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Gritsai-MS-Thesis/tree/master/paper), [Slides](https://github.com/intsystems/Gritsai-MS-Thesis/blob/master/slides/mipt_nir.pdf), [Code](https://github.com/intsystems/Gritsai-MS-Thesis/tree/master/src) | -| Ildar Khabutdinov | 2 | Исправление грамматических ошибок в домене низкоресурсных языков | [Grabovoy A.V.](https://andriygav.github.io) | [Publication](https://github.com/intsystems/masters-thesis/blob/main/SpellingCorrectionFinal.pdf), [Publication](https://github.com/intsystems/masters-thesis/blob/main/PCS315-3%20(1).pdf), [Slides](https://github.com/intsystems/masters-thesis/blob/main/presentation.pdf)| -| Marat Khusainov | 2 | Understanding the Plasticity of Neural Networks Employed in GFlowNets| Samsonov S.V. | [Paper](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/paper/main.pdf), [Slides](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/slides/slides.pdf), [Code](https://github.com/intsystems/Khusainov-MS-Thesis/tree/master/code) | -| Petrushina Kseniia | 2 | Detection of Multimodal Hallucinations Based on Internal Representations and Activations of Models | [Panchenko A. I.](https://msc.skoltech.ru/alexanderpanchenko) | [Publication 1](https://aclanthology.org/2025.naacl-srw.28/) [Publication 2](https://arxiv.org/abs/2503.15948), [Slides](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/slides/Slides2025Petrushina.pdf), [Paper](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/paper/NIR2025Petrushina.pdf), [Code](https://github.com/intsystems/Petrushina-MS-Thesis/tree/master/code) | - -#### First Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Dorin Daniil | 1 | Enhancing fMRI Data Decoding with Spatiotemporal Characteristics in Limited Dataset | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://drive.google.com/file/d/1lwVA3lI0CHYr8JWr9bBvvv9ZkaZdbNvf/view?usp=drive_link), [Slides](https://drive.google.com/file/d/1aTMGkRvo1RFinYyP8Fcs1TkQYPMiRe6u/view?usp=sharing), [Code](https://github.com/intsystems/Spatial-and-Temporal-Characteristics)| -| Nikitina Maria | 1 | Методы векторного представления глубоких генеративных моделей | [Bakhteev O. Yu.](https://intsystems.github.io/people/bakhteev_oy/index.html) [Bishuk A. Yu.](https://intsystems.github.io/people/bishuk_ay/index.html) | [Paper](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/paper), [Code](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/code), [Slides](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/slides) | -| Latypov Ilgam | 1 | Functional multi-armed bandit and the best function identification problems | [Y.V. Dorn](https://scholar.google.com/citations?user=ByIc-l8AAAAJ&hl=ru) | [Paper](https://arxiv.org/pdf/2503.00509), [Paper Int](https://github.com/intsystems/Latypov-MS-FMAB/blob/main/paper/FMAB.pdf) [Slides](https://github.com/intsystems/Latypov-MS-FMAB/blob/main/slides/FMAB_presentation.pdf), [Code](https://github.com/intsystems/Latypov-MS-FMAB/tree/main)| -| Semkin Kirill | 1 | Time series classification approaches through NeuralODE | Strijov V.V | [Paper](https://github.com/intsystems/n_ode/blob/main/paper/node_classification_Semkin.pdf), [Code](https://github.com/intsystems/n_ode/tree/main), [Slides](https://github.com/intsystems/n_ode/blob/main/slides/neural_ode_Semkin_slides.pdf) | -| Nikita Kiselev | 1 | Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://link.springer.com/article/10.1134/S1064562424601987), [Code](https://github.com/intsystems/landscape-hessian/tree/validation/code), [Slides](https://github.com/intsystems/landscape-hessian/blob/validation/slides/main.pdf) | -| Igor Ignashin | 1 | Theory for Adaptive Loss Scaling | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Ignashin_MS_thesis/blob/master/paper/_NIPS__Proof_for_ALSO-2.pdf), [Code](https://github.com/intsystems/Ignashin_MS_thesis/tree/master/code), [Slides](https://github.com/intsystems/Ignashin_MS_thesis/blob/master/slides/_NIR2025_1__Transport_Ski_Resort___ALSO_convergence%20(1).pdf) | -| Andrey Veprikov | 1 | Оптимальное управление в системах машинного обучения с обратной связью: предотвращение деградации и оттока пользователей | [Khritankov A.S.](https://scholar.google.com/citations?user=OtxWKpMAAAAJ&hl=en) | [Paper](https://github.com/intsystems/Veprikov-MS-Thesis/blob/main/paper/%D0%A2%D0%B5%D0%B7%D0%B8%D1%81%D1%8B%20%D0%92%D0%B5%D0%BF%D1%80%D0%B8%D0%BA%D0%BE%D0%B2.pdf), [Code](https://github.com/intsystems/Veprikov-MS-Thesis/tree/main/dynamic-systems-model), [Slides](https://github.com/intsystems/Veprikov-MS-Thesis/blob/main/slides/67_%D0%BA%D0%BE%D0%BD%D1%84%D0%B5%D1%80%D0%B5%D0%BD%D1%86%D0%B8%D1%8F_%D0%9C%D0%A4%D0%A2%D0%98.pdf) | -| Okhotnikov Nikita | 1 | Low rank attention denoising | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/LowRankAttentionDenoising/blob/main/paper/main.pdf), [Slides](https://github.com/intsystems/LowRankAttentionDenoising/tree/main/slides), [Code](https://github.com/intsystems/LowRankAttentionDenoising/tree/main/code/adapter)| -| Voznyuk Anastasia | 1 | Анализ внутренних представлений языковых моделей для поиска сгенерированных документов| [Grabovoy A.V.](https://andriygav.github.io) | [Paper 1](https://arxiv.org/pdf/2503.03601), [Paper 2](https://github.com/intsystems/Internal_States_Level_MachineGen_NIR/blob/main/paper/m1p.pdf) [Code](https://github.com/intsystems/Internal_States_Level_MachineGen_NIR/tree/main/code), [Slides](https://github.com/intsystems/Internal_States_Level_MachineGen_NIR/blob/main/slides/16_05_2024_NIR_Report.pdf) | -| Terentyev Alexander | 1 | Inverse problems in modeling neural partial differential equations | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/intsystems/Terentyev-MS-InPDE/blob/main/paper/Inverse_nPDE__Paper_.pdf), [Code](https://github.com/intsystems/Terentyev-MS-InPDE/tree/main/experiments/base), [Slides](https://github.com/intsystems/Terentyev-MS-InPDE/blob/main/slides/Inverse_problems_in_modeling_neural_partial_differential_equations_Slides.pdf) | -| Babkin Petr | 1 | Position Informed Convolution for Multi-Agent Computer Vision | Shubin N.Y. | [Paper](https://github.com/intsystems/position-informed-convolution/blob/main/assets/PIC.pdf), [Code](https://github.com/intsystems/position-informed-convolution/tree/main/code), [Slides](https://github.com/intsystems/position-informed-convolution/blob/main/assets/PIC_slides.pdf) | -| Nasyrov Ruslan | 1 | Marked Temporal Point Process with Neural ODE |[Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/intsystems/DM-TPP-with-Neural-ODE/blob/master/paper/Neural_ODE_thesis%20(1).pdf), [Code](https://github.com/intsystems/DM-TPP-with-Neural-ODE/tree/master/code), [Slides](https://github.com/intsystems/DM-TPP-with-Neural-ODE/blob/master/slides/DM_TPP_presentation.pdf) | -| Kreinin Matvei | 1 | Нормализирующие потоки для перевода КТ изображений | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Kreinin-MS-Thesis/blob/main/paper/paper_xFlow.pdf), [Code](https://github.com/intsystems/Kreinin-MS-Thesis/tree/main/src), [Slides](https://github.com/intsystems/Kreinin-MS-Thesis/blob/main/slides/slides.pdf) | -| Zabarianska Iryna | 1 | Параметрические методы решения задачи о мосте Шредингера | [Korotin A.A.](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Paper](https://github.com/Akshiira/SB-problem/blob/173f0b00060128f9e727c347778627d1467b1b5e/Abstract.pdf), [Code](https://github.com/Akshiira/SB-problem/blob/0da718188c417ba7b637efecd74980dc3e8b7bf5/Jaakkola%20Light%20SB.py), [Slides](https://github.com/Akshiira/SB-problem/blob/0da718188c417ba7b637efecd74980dc3e8b7bf5/%D0%9F%D1%80%D0%B5%D0%B7%D0%B5%D0%BD%D1%82%D0%B0%D1%86%D0%B8%D1%8F_%D0%9D%D0%98%D0%A0_6_%D1%81%D0%B5%D0%BC%D0%B5%D1%81%D1%82%D1%80.pdf) | -| Sapronov Yuri | 1 | Solving the Ranking Problem Using Continuous Optimization Methods | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ) | [Paper](https://github.com/intsystems/LtR_intsys/blob/main/paper.pdf), [Code](https://github.com/intsystems/LtR_intsys/tree/main/Transformer), [Slides](https://github.com/intsystems/LtR_intsys/blob/main/report.pdf) | - - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Firsov Sergey | 4 | Neural architecture search with target hardware control | [Bakhteev O. Y.](https://bahleg.site/publications) | [Paper](https://github.com/intsystems/Firsov_FBNet/blob/master/paper/main_paper.pdf), [Code](https://github.com/intsystems/Firsov_FBNet/tree/master/code), [Slides](https://github.com/intsystems/Firsov_FBNet/blob/master/slides/slides.pdf)| -| Zadvornov Egor | 4 | Forecasting social trends with high volatility | Malkov A. S. | [Paper](https://github.com/intsystems/Zadvornov_Egor_paper/blob/master/paper/Zadvornov2024VolatilityTimeSeries.pdf), [Code](https://github.com/intsystems/Zadvornov_Egor_paper/tree/master/src), [Slides](https://github.com/intsystems/Zadvornov_Egor_paper/blob/master/slides/Slides_for_paper_2025%20(2).pdf)| -| Meshkov Vladislav | 4 | ConvNets Landscape Convergence: Hessian-Based Analysis of Matricized Networks | [Grabovoy A.V.](https://andriygav.github.io ) | [Paper](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks), [Slides](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/slides/main.pdf)| -| Papay Ivan | 4 | Ordinal Classification Using Partially Ordered Feature Sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/intsystems/Papay-BS-Thesis/blob/master/code/mixtures.ipynb) [Paper](https://github.com/intsystems/Papay-BS-Thesis/blob/master/paper/PartialOrders.pdf) [Slides](https://github.com/intsystems/Papay-BS-Thesis/blob/master/slides/PartialOrders_slides.pdf)| -| Nabiev Muhammadsharif | 4 | Inductive Bias in Model Selection | [Bakhteev O. Y.](https://bahleg.site/publications) | [Paper](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/IB_in_model_selection.pdf), [Code](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/analysis/symreg_circles.ipynb), [Slides](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/slides.pdf)| -| Anastasiia Linich | 4 | Топологический анализ математических доказательств, генерируемых большими языковыми моделями на формальном языке Lean4 | Barannikov S.A. | [Code](https://github.com/khilling/diploma/tree/main), [Paper](https://github.com/khilling/diploma/blob/main/srw_text.pdf), [Slides](https://github.com/khilling/diploma/blob/main/srw_presentation.pdf) | -| Rubtsov Denis | 4 | Сходимость с оценкой вероятностей больших отклонений для задач выпуклой оптимизации и седловых задач в условиях повышенной гладкости| [Gasnikov A.V.](https://ru.wikipedia.org/wiki/Гасников,_Александр_Владимирович) | [Paper](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/paper/RUBTSOV_DIPLOMA.pdf), [Code](https://github.com/intsystems/Rubtsov-BS-thesis/tree/master/code), [Slides](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/slides/Rubtsov_bachelor_diploma_slides.pdf)| -| Khafizov Fanis | 4 | Adaptive Compression in Distributed Optimization | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/slides)| -| Eynullayev Altay | 4 | Forecasting models in riemannian phase space | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/paper/paper.pdf), [Code](https://github.com/intsystems/Eynullayev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/slides/slides_diplom(9).pdf)| -| Karpeev Gleb | 4 | Порождающие модели для прогнозирования наборов временных рядов | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/intsystems/2024-Project-152/blob/master/code), [Paper](https://github.com/intsystems/2024-Project-152/blob/master/paper/diploma.pdf), [Slides](https://github.com/intsystems/2024-Project-152/blob/master/slides/presentation%20Karpeev%20latest.pdf) | -| Stepanov Ilya| 4 | Using Synthetic Data Obtained by Generative Neural Networks to Improve the Quality of Detection Models | [Grabovoy A.V.](https://andriygav.github.io ) | [Paper](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master/paper), [Code](https://github.com/ILIAHHne63/PaperFramework), [Slides](https://github.com/intsystems/Stepanov-BS-Thesis/blob/master/slides/main.pdf)| -| Rebrikov Alexey | 4 | Investigation of Neural Network Sparsification Mechanisms Based on Weight Importance | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/NoblFriend/bachelor-thesis/tree/IDA), [Slides](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/slides/main.pdf)| -| Fedor Sobolevsky | 4 | Application of Large Language Models for Hierarchical Summarization of Scientific Texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/intsystems/Sobolevsky-BS-Thesis/tree/main/code),[Paper](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/paper/Sobolevsky2025BSThesis.pdf), [Slides](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/slides/Sobolevsky2024Presentation.pdf) | -| Kasiuk Vadim | 4 | Application of compression operators in distributed optimization problems | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/KasiukVadim/BacDip24_25/blob/main/docs/Kasiuk2024CompressionForDistributedOptimization.pdf), [Code](https://github.com/KasiukVadim/BacDip24_25/blob/main/notebooks/MethodsNotebook.ipynb), [Slides](https://github.com/KasiukVadim/BacDip24_25/blob/main/slides/Kasiuk2024CompressionForDistributedOptimization_slides_pdf__Copy_%20(1).pdf)| - -### 2024 FALL - -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -|Viktor Pankratov|2|Probabilistic topic modeling|[Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov)|[Paper](https://github.com/intsystems/PankratovPHD2024/tree/main/paper),[Code](https://github.com/intsystems/PankratovPHD2024/tree/main/code),[Slides](https://github.com/intsystems/PankratovPHD2024/tree/main/slides)| -|Konstantin Yakovlev | 1 | Tensor Methods in Federated Learning| [Gasnikov A.V.](https://scholar.google.com/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Publication 1](https://openreview.net/pdf?id=uvFDaeFR9X), [Publication 2](https://aclanthology.org/2024.findings-emnlp.345/) | -|Grigoriy Ksenofontov | 1 | Discrete Schrödinger Bridges | [Korotin A.A.](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Publication](https://openreview.net/forum?id=LikKyNlzgP), [Code](https://github.com/gregkseno/ipmf), [Slides](https://www.overleaf.com/read/jvfmrzpbdbzw#343d8d) | - - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Galina Boeva | 2 | Efficient aggregation by labels for the problem of event sequences | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Publication](https://ebooks.iospress.nl/volumearticle/70171?_gl=1*1kzsn7p*_up*MQ..*_ga*MTE2NzcyNzQzLjE3MzM4MjMzNDE.*_ga_6N3Q0141SM*MTczMzgyMzM0MS4xLjAuMTczMzgyMzM0MS4wLjAuMA..), [Paper](https://arxiv.org/abs/2303.00280), [Slides](https://github.com/Gaechka777/NIR24_25/blob/master/slides/slides_nir_11sem.pdf), [Code](https://github.com/Gaechka777/NIR24_25)| -| Nikita Kornilov | 2 | Optimal Flow Matching: Learning Straight Trajectroies in Just One Step | [Gasnikov A.V.](https://scholar.google.com/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao)| [Publication](https://openreview.net/forum?id=kqmucDKVcU), [Paper](https://github.com/Jhomanik/Optimal-Flow-Matching/blob/main/paper/Optimal_Flow_Matching_NIPS.pdf), [Slides](https://github.com/Jhomanik/Optimal-Flow-Matching/blob/main/slides/OFM_Research_Fall_2024.pdf), [Code](https://github.com/Jhomanik/Optimal-Flow-Matching/tree/main)| -| Eduard Vladimirov | 2 | Generative Causal Inference for BCI | Strijov V.V. | [Paper](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/paper/Vladimirov2024GenerativeCIPaper.pdf), [Slides](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master/slides), [Code](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master/code)| -| Arina Chumachenko | 2 | Controlled Image Editing Mechanisms Based on Diffusion Models | [Oseledets I.V.](https://scholar.google.com/citations?user=5kMqBQEAAAAJ&hl=ru) | [Paper](https://github.com/arina-chumachenko/Chumachenko_NIR2024/tree/master/paper), [Slides](https://github.com/arina-chumachenko/Chumachenko_NIR2024/tree/master/slides), [Code](https://github.com/arina-chumachenko/Chumachenko_NIR2024/tree/master/code) | -| Marat Khusainov | 2 | Understanding the plasticity of neural networks employed in GFlowNets | Samsonov S.V. | [Paper](https://github.com/maratkhusainov/NIR-main/blob/master/paper/main.pdf), [Slides](https://github.com/maratkhusainov/NIR-main/blob/master/slides/slides.pdf), [Code](https://github.com/maratkhusainov/NIR-main/tree/master/code)| -| Kseniia Petrushina | 2 | Detection of Hallucinations in Multimodal Models Based on Internal Representations | [Alexander Panchenko](https://msc.skoltech.ru/alexanderpanchenko) | [Paper](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/paper/NIR2024Petrushina.pdf), [Slides](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/slides/NIR2024Slides.pdf), [Code](https://github.com/intsystems/Petrushina_2024_NIR/tree/master/code)| -| German Gritsai | 2 | Verification of artificially generated text fragments | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/grgera/Text-detection-dataset/blob/main/nir/papers/2410.14677v1.pdf), [Paper 2](https://github.com/grgera/Text-detection-dataset/blob/main/nir/papers/2411.07343v1.pdf), [Paper 3](https://github.com/grgera/Text-detection-dataset/blob/main/nir/papers/2411.11736v1.pdf), [Slides](https://github.com/grgera/Text-detection-dataset/blob/main/nir/slides/mipt_nir-5.pdf), [Code](https://github.com/grgera/Text-detection-dataset/tree/main) | -| Ildar Khabutdinov | 2 | Исправление Грамматических Ошибок в Домене Низкоресурсных Языков | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/depinwhite/masters-thesis/blob/main/SpellingCorrectionFinal.pdf), [Paper 2](https://github.com/depinwhite/masters-thesis/blob/main/PCS315-3%20(1).pdf), [Slides](https://github.com/depinwhite/masters-thesis/blob/main/Khabutdinov2024(S11)Report.pdf) | -| Bair Mikhailov | 2 | Сегментация и объяснимое машинное обучение в задачах радиологии| [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Slides](https://github.com/MikhailovBair/Mikhailov-MS-Thesis/blob/master/slides/TSR_MIkhailov_Bair.pptx), [Poster](https://github.com/MikhailovBair/Mikhailov-MS-Thesis/blob/master/slides/Mikhailov%202024.pdf), [Code](https://github.com/MikhailovBair/Mikhailov-MS-Thesis)| - -#### First Year Master Students - -| Student | Year | Topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Nikita Kiselev | 1 | Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://arxiv.org/abs/2409.11995), [Code](https://github.com/kisnikser/landscape-hessian), [Slides](https://github.com/kisnikser/landscape-hessian/blob/main/slides/main.pdf) | -| Daniil Dorin | 1 | Декодирование визуальных стимулов из мультимодальных сигналов мозга | [Grabovoy A.V.](https://andriygav.github.io) | [Publication](https://link.springer.com/article/10.1007/s13755-024-00315-5), [Paper1](https://drive.google.com/file/d/1XD056tNYgLA3KNU5s8w6mxgR2W5tXUE-/view?usp=drive_link), [Paper2](https://drive.google.com/file/d/1Vqa48auYId8cRfX20Y4T-Irv3kLDMF3V/view?usp=sharing), [Code1](https://github.com/intsystems/CreationOfIntelligentSystems_Simultaneous_fMRI-EEG), [code2](https://github.com/DorinDaniil/Spatial-and-Temporal-Characteristics), [Slides](https://ru.overleaf.com/read/bcxqhzhdndzv#83b8ae) | -| Kirill Semkin | 1 | Time series classification in parameters space using NeuralODE | Strijov V.V. | [Paper](https://github.com/intsystems/n_ode/blob/hypothesis_exp/docs/node_classification_Semkin.pdf),[Code](https://github.com/intsystems/n_ode/tree/hypothesis_exp/experiments),[Slides](https://github.com/intsystems/n_ode/blob/hypothesis_exp/slides/neural_ode_Semkin_slides.pdf), | -| Andrey Veprikov | 1 | The optimal control problem in artificial intelligence systems with feedback loop | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Paper](https://arxiv.org/abs/2405.02726), [Code](https://gitlab.com/repeated_ml/dynamic-systems-model),[Slides](https://github.com/Vepricov/Veprikov-BS-Thesis/blob/master/slides/_Ms_2024__presentation.pdf) | -| Ilgam Latypov | 1 | γ-Competitiveness: An Approach to Multi-Objective Optimization with High Computation Costs in Lipschitz Functions | [Dorn Y.V.](https://labmmo.ru/team/dorn.html) | [Paper](https://arxiv.org/abs/2410.03023), [Publication](https://rdcu.be/elTnX), [Code](https://github.com/xxamxam/paper1), [Slides](https://www.overleaf.com/read/kxtsrvbmqcxx#bd0852) | -| Ignashin Igor | 1 | Stochastic Correspondences Frank-Wolfe | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Ignashin_MS_thesis/blob/master/paper/2024_Stochastic_Correspondence-2.pdf), [Code](https://github.com/ThunderstormXX/mmo_tm), [Slides](https://github.com/intsystems/Ignashin_MS_thesis/blob/master/slides/_NIR__Stochastic_Correspondences_Frank_Wolfe.pdf) | -| Babkin Petr | 1 | Position Informed Convolution for Multi-Agent Curve Detection | Shubin N.Y. | [Paper1](https://github.com/petr-parker/position-informed-convolution/blob/main/assets/PIC.pdf), [Code1](https://github.com/petr-parker/position-informed-convolution/tree/main/code), [Paper2](https://github.com/intsystems/2023-Project-120/blob/master/paper/main.pdf), [Code2](https://github.com/intsystems/2023-Project-120/tree/master/code), [Slides](https://github.com/petr-parker/position-informed-convolution/blob/main/assets/PIC_slides.pdf) | -| Terentyev Alexander | 1 | Inverse problems in modeling neural partial differential equations | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/lopate/lagrange_classification/blob/master/paper/SNCS-D-24-08760.pdf), [Code](https://github.com/lopate/lagrange_classification/tree/master/code), [Slides](https://github.com/lopate/inverse-npde/blob/main/slides/Inverse_problems_in_modeling_neural_partial_differential_equations_Slides.pdf) | -| Nasyrov Ruslan | 1 | Decomposition of uncertainty in neural networks |[Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/intsystems/uncertainty_quantification_2024/blob/master/paper/Calibration_thesis.pdf), [Code](https://github.com/intsystems/uncertainty_quantification_2024/tree/master/code), [Slides](https://github.com/intsystems/uncertainty_quantification_2024/blob/master/slides/Calibration_Presentation_Shortened%20(1).pdf) | -| Zabarianska Iryna | 1 | Параметрические методы решения задачи о мосте Шредингера |[Alexander Korotin](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Paper](https://arxiv.org/abs/2408.01753), [Code](https://github.com/Akshiira/-5-/blob/main/main.py), [Slides](https://github.com/Akshiira/-5-/blob/main/%D0%9F%D1%80%D0%B5%D0%B7%D0%B5%D0%BD%D1%82%D0%B0%D1%86%D0%B8%D1%8F_%D0%9D%D0%98%D0%A0_5_%D1%81%D0%B5%D0%BC%D0%B5%D1%81%D1%82%D1%80.pdf) | -| Nikitina Maria | 1 | Методы векторного представления глубоких генеративных моделей | [Bakhteev O. Yu.](https://intsystems.github.io/people/bakhteev_oy/index.html) [Bishuk A. Yu.](https://intsystems.github.io/people/bishuk_ay/index.html) | [Paper](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/paper), [Code](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/code), [Slides](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/slides) | -| Kreinin Matvei | 1 | Генерация обучающей выборки с помощью ограниченного набора данных | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/kreininmv/Pseudo-labeling/blob/master/src/article/article.pdf), [Code](https://github.com/kreininmv/Pseudo-labeling/tree/master/experiments), [Slides](https://github.com/kreininmv/Pseudo-labeling/blob/master/src/slides/slides.pdf) | -| Sapronov Yuri | 1 | Solving the ranking problem with continuous optimization methods | [Gasnikov A. V.](https://www.hse.ru/org/persons/49503846/) | [Paper](https://github.com/Sapr7/Learning-To-Rank/blob/sapr/icml2025.pdf), [Code](https://github.com/Sapr7/Learning-To-Rank/tree/bobr), [Slides](https://github.com/Sapr7/Learning-To-Rank/blob/sapr/%D0%9D%D0%98%D0%A0_presentation.pdf) | -| Voznyuk Anastasia | 1 | Анализ неопределенности и внутренних представлений языковых моделей для поиска сгенерированных документов| [Grabovoy A.V.](https://andriygav.github.io) | [Paper 1](https://arxiv.org/abs/2410.14677), [Paper 2](https://arxiv.org/abs/2410.02343), [Paper 3](https://arxiv.org/abs/2411.11736), [Code](https://github.com/intsystems/Uncertainty_MachineGen_NIR/blob/main/code), [Slides](https://github.com/intsystems/Uncertainty_MachineGen_NIR/blob/main/slides/21_12_2024_NIR_Report.pdf) | -| Okhotnikov Nikita | 1 | Improving algorithmic alignment with autoregressive memory | [Grabovoy A.V.](https://andriygav.github.io) | [Slides](https://github.com/Wayfarer123/ExtraARM-GNN/blob/master/slides/main.pdf), [Code](https://github.com/Wayfarer123/ExtraARM-GNN/tree/master/code), [Paper](https://github.com/Wayfarer123/ExtraARM-GNN/tree/master/paper)| - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Papay Ivan | 4 | Ordinal Classification Using Partially Ordered Feature Sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/papayiv/Papay-BS-Thesis/blob/main/code/experiments/mixtures.ipynb) [Paper](https://github.com/papayiv/Papay-BS-Thesis/blob/main/paper/PartialOrders.pdf) [Slides](https://github.com/papayiv/Papay-BS-Thesis/blob/main/slides/PartialOrders_slides.pdf)| -| Meshkov Vladislav | 4 | ConvNets Landscape Convergence: Hessian-Based Analysis of Matricized Networks | [Grabovoy A.V.](https://andriygav.github.io ) | [Paper](https://github.com/Drago160/Meshkov-paper/blob/master/paper/main.pdf), [Code](https://github.com/Drago160/Meshkov-paper/tree/master), [Slides](https://github.com/Drago160/Meshkov-paper/blob/master/slides/main.pdf)| -| Stepanov Ilia | 4 | The use of synthetic data obtained using a generative neural network to improve the quality of detection models | [Grabovoy A.V.](https://andriygav.github.io ) | [Paper](https://github.com/ILIAHHne63/Stepanov_Ilia_paper/tree/master/paper), [Code](https://github.com/ILIAHHne63/Stepanov_Ilia_paper/tree/master/code), [Slides](https://github.com/ILIAHHne63/Stepanov_Ilia_paper/tree/master/slides/paper_slides)| -| Nabiev Muhammadsharif | 4 | Inductive Bias in Model Selection | Bakhteev O. Y. | [Paper](https://github.com/mikhmed-nabiev/IB-in-model-selection/blob/main/papers/IB_in_model_selection.pdf), [Code](https://github.com/mikhmed-nabiev/IB-in-model-selection/tree/main/src), [Slides](https://github.com/mikhmed-nabiev/IB-in-model-selection/blob/main/papers/Nabiev2024FirstReport.pdf)| -| Zadvornov Egor | 4 | Forecasting social trends with high volatility | Malkov A. S. | [Paper](https://github.com/LoveMyWork/Zadvornov_Egor_paper/blob/master/paper/Zadvornov2024VolatilityTimeSeries.pdf), [Code](https://github.com/LoveMyWork/Zadvornov_Egor_paper/tree/master/src), [Slides](https://github.com/LoveMyWork/Zadvornov_Egor_paper/blob/master/slides/Slides_for_paper.pdf)| -| Rebrikov Aleksei | 4 | Investigation of Neural Network Sparsification Mechanisms Based on Weight Importance | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/NoblFriend/bachelor-thesis/tree/IDA), [Slides](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/slides/main.pdf)| -| Firsov Sergey | 4 | Neural architecture search with target hardware control | [Bakhteev O. Y.](https://bahleg.site/publications) | [Paper](https://github.com/intsystems/Firsov_FBNet/blob/master/paper/Firsov_FBNet_0.pdf), [Code](https://github.com/intsystems/Firsov_FBNet/tree/master/src), [Slides](https://github.com/intsystems/Firsov_FBNet/blob/master/slides/slides.pdf)| -| Khafizov Fanis | 4 | Adaptive Compression in Distributed Optimization | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/slides)| -| Eynullayev Altay | 4 | Forecasting models in riemannian phase space | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/paper/paper.pdf), [Code](https://github.com/intsystems/Eynullayev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/slides/slides_diplom(9).pdf)| -| Rubtsov Denis | 4 | Сходимость с оценкой вероятностей больших отклонений для задач выпуклой оптимизации и седловых задач в условиях повышенной гладкости| [Gasnikov A.V.] | [Paper](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/paper/Сходимость_с_оценкой_вероятностей_больших_отклонений_для_задач_выпуклой_оптимизации_и_седловых_задач_в_условиях_повышенной_гладкости%20(1).pdf), [Code](https://github.com/intsystems/Rubtsov-BS-thesis/tree/master/code), [Slides](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/slides/Rubtsov_bachelor_diploma_slides.pdf)| -| Kasiuk Vadim | 4 | Application of compression operators in distributed optimization problems | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/KasiukVadim/BacDip24_25/blob/main/docs/Kasiuk2024CompressionForDistributedOptimization.pdf), [Code](https://github.com/KasiukVadim/BacDip24_25/blob/main/notebooks/MethodsNotebook.ipynb), [Slides](https://github.com/KasiukVadim/BacDip24_25/blob/main/slides/Kasiuk2024CompressionForDistributedOptimization_slides_pdf__Copy_%20(1).pdf)| -| Fedor Sobolevsky | 4 | Application of Large Language Models for Hierarchical Summarization of Scientific Texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/intsystems/Sobolevsky-BS-Thesis/tree/main/code),[Paper](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/paper/Sobolevsky2024MindMaps.pdf), [Slides](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/slides/Sobolevsky2024Presentation.pdf) | -| Anastasiia Linich | 4 | Топологический анализ математических доказательств, генерируемых большими языковыми моделями на формальном языке Lean4 | Barannikov S.A. | [Code](https://github.com/khilling/diploma/tree/main), [Paper](https://github.com/khilling/diploma/blob/main/srw_text.pdf), [Slides](https://github.com/khilling/diploma/blob/main/srw_presentation.pdf) | -| Karpeev Gleb | 4 | Порождающие модели для прогнозирования (наборов временных рядов) в метрическом вероятностном пространстве | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/intsystems/2024-Project-152/blob/master/code/gen_score_based_models.ipynb), [Paper](https://github.com/intsystems/2024-Project-152/blob/master/paper/diploma.pdf), [Slides](https://github.com/intsystems/2024-Project-152/blob/master/slides/Karpeev.pdf) | - - -### 2024 SPRING -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| [Vasiliy Alekseev](http://www.machinelearning.ru/wiki/index.php?title=User:Alvant) | 4 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper1](https://www.dialog-21.ru/media/4281/alekseevva.pdf), [Paper2](https://aclanthology.org/2020.lrec-1.833), [Paper3](https://www.sciencedirect.com/science/article/pii/S0169023X21000483); [Slides1](http://www.machinelearning.ru/wiki/images/4/49/Iterative_improvement_of_an_additive_regularized_topic_model.pdf), [Slides2](http://www.machinelearning.ru/wiki/images/f/f2/Determination_of_the_Number_of_Topics_Intrinsically_Is_It_Possible_.pdf) | -| Novitskii Vasilii | 3 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization| [Gasnikov A.V.](https://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Paper 3](https://proceedings.mlr.press/v162/gasnikov22a.html), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing), [Text](https://disk.yandex.ru/i/vJCKpWGPNBTLTQ) | -| Alexey Grishanov | 2 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper 1](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Paper 2](https://2024.naacl.org/program/accepted_papers/), [Code](https://github.com/milteam/unsupervised-summary-based-segmentation), [Slides](https://github.com/intsystems/GrishanovPHD2022/blob/main/slides/Grishanov%20DDPG%20(RL%20for%20online%20recsys).pdf) | -| Panchenko Sviatoslav | 2 | Graph diffusion models for the task of brain signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) |[Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code), [Slides](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanhenkoIDP2022slides.pdf), [Paper1](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoPaper1Translated.pdf)| -| Pavel Severilov | 2 | Decoding of multimodal signals of brain activity | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper1](https://github.com/severilov/phd-thesis/blob/main/slides/NabievSeverilov2024SignalToAudio.pdf) [Paper2](https://github.com/severilov/phd-thesis/blob/main/slides/noether_lnn_severilov_eng.pdf) [Thesis](https://github.com/severilov/phd-thesis/blob/main/report/phd_thesis.pdf), [Code](https://github.com/severilov/phd-thesis), [Slides Paper1](https://github.com/severilov/phd-thesis/blob/main/slides/NabievSeverilov_EEG_audio2024.pdf)| -| Denis Tikhonov | 2 | Attractor reconstruction for linearized system with miltilinear map | [Strijov V.V.](http://www.ccas.ru/strijov/) |[Code](https://github.com/Denis-Tihonov/TensorDynamic/tree/main/code), [Slides Paper1](https://github.com/Denis-Tihonov/TensorDynamic/blob/main/slides/Tikhonov2024TensorReconstruction.pdf)| -| Viktor Pankratov | 1 | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/PankratovPHD2024/blob/main/paper/Pankratov_MS_Thesis.pdf),[Code](https://github.com/intsystems/PankratovPHD2024/tree/main/code),[Slides](https://github.com/intsystems/PankratovPHD2024/blob/main/slides/slides_spring2024.pdf) | - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Klypa Roman | 2 | Generative modeling for protein structure and interactions | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/) | [Paper](https://github.com/romanklypa/intsystems_thesis/blob/main/icml2024.pdf), [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/slides_nir2024spring.pdf), [Code](https://github.com/ljk-rk/MolBindDif)| -| Kovaleva Maria | 2 | Addition of external information for enhancement of local embeddings for event sequences data models | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://arxiv.org/pdf/2404.02047), [Thesis](https://github.com/MarKovka20/transactions_gen_models/blob/main/thesis.pdf), [Slides](https://github.com/MarKovka20/transactions_gen_models/blob/main/Kovaleva_Maria_predefence_for_MIPT.pdf), [Code](https://github.com/MarKovka20/transactions_gen_models/tree/main)| -| Grigoriy Ksenofontov | 2 | Adversarial Schrödinger Bridges | [Roman Isachenko]() | [Code](https://github.com/gregkseno/masters-thesis/blob/master/code/adversarial_ipfp.ipynb), [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/4th/4th%20term.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/paper.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/mipt.pdf) | -| Konstantin Yakovlev | 2 | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/paper/HPO.pdf), [Slides](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/slides/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/HyperOpt/tree/main)| -| Tolmachev Alexander | 2 | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Paper](https://openreview.net/forum?id=huGECz8dPp), [Paper2](https://arxiv.org/pdf/2403.02187), [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Report.pdf) | -| Polina Barabanshchikova | 2 | Tverberg type theorems | [Polyanskii A.A.](http://polyanskii.com/)| [Draft](https://github.com/pollinab/MasterThesis/blob/main/Tverberg_graphs_on_hyperboloid.pdf), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_Tverberg_SVM.pdf), [Code](https://github.com/pollinab/MasterThesis/blob/main/TverbergSVM.ipynb) -| Alkin Emil | 2 | Expressive Power of Recurrent Neural Networks, II | [Ivan Oseledets](https://faculty.skoltech.ru/people/ivanoseledets) |[Draft](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/tensors_strong_hyp_sketch.pdf), [Slides](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/Slides(S12).pdf), [Code](https://github.com/AlkinEmil/MasterThesisPublic) - -#### First Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Boeva Galina | 1 | Label Attention Network for Temporal Sets prediction | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Full Paper](https://github.com/Gaechka777/NIR_2024/blob/main/full_paper.pdf) [Paper](https://github.com/Gaechka777/NIR_2024/blob/main/paper/Boeva2024LabelRelation.pdf), [Slides](https://github.com/Gaechka777/NIR_2024/blob/main/slides/Final_presentation_.pdf), [Code](https://github.com/Gaechka777/NIR_2024/tree/main)| -| Chumachenko Arina | 1 | Machine learning methods for functional brain mapping | [Sharaev M. G.](https://faculty.skoltech.ru/people/msharaev) | [Paper](https://github.com/arina-chumachenko/NIR2024/tree/main/paper), [Slides](https://github.com/arina-chumachenko/NIR2024/blob/main/slides/ChumachenkoNIR2024.pdf), [Code](https://github.com/arina-chumachenko/NIR2024/tree/main) | -| Marat Khusainov | 1 | Adaptive sampling methods using diffusion models | [Samsonov S.V.]() | [Paper](https://github.com/maratkhusainov/NIR2024-main/blob/master/paper/paper.pdf), [Slides](https://github.com/maratkhusainov/NIR2024-main/blob/master/slides/slides.pdf) , [Code](https://github.com/maratkhusainov/NIR2024-main/tree/master/code) | -| Kornilov Nikita | 1 | Optimal Flow Matching | Gasnikov A.V. | [Paper](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/paper/Optimal_Flow_matching_v17_05.pdf), [Slides](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/slides/OFM_NIR_Spring_2024.pdf), [Code](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/notebooks/ofm_alae.ipynb) | -| Kseniia Petrushina | 1 | Quantifying image realism via language model reasonings | [Alexander Panchenko](https://msc.skoltech.ru/alexanderpanchenko) | [Paper](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/paper/Quantifying2024Petrushina.pdf), [Slides](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/slides/Quantifying2024Slides.pdf) , [Code](https://github.com/intsystems/Petrushina_2024_NIR/tree/master/code) | -| Parviz Karimov | 1 | Representation learning for collections of data | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/IPPK93/Karimov_2024_NIR/blob/master/paper/paper.pdf), [Slides](https://github.com/IPPK93/Karimov_2024_NIR/blob/master/slides/slides.pdf), [Code](https://github.com/IPPK93/Karimov_2024_NIR/tree/master) | -| Dmitry Protasov | 1 | Automatic Music Transcription | Ivan Matveev | [Paper](https://github.com/intsystems/2024-Project-165/blob/master/paper/paper_spring_2024.pdf), [Slides](https://github.com/intsystems/2024-Project-165/blob/master/paper/final_talk_18_05.pdf), [Code](https://github.com/intsystems/2024-Project-165/tree/master/code) | -| German Gritsai | 1 | Automatic Detection of Machine Generated Texts | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/grgera/Text-detection-dataset/blob/main/nir/poisk_iskusstveno_sgen_frags.pdf), [Paper 2](https://github.com/grgera/Text-detection-dataset/blob/main/nir/Need%20More%20Tokens.pdf), [Slides](https://github.com/grgera/Text-detection-dataset/blob/main/nir/mipt_nir-3.pdf) | - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Nikita Kiselev | 4 | Bayesian Sample Size Estimation | [Grabovoy A. V.](https://andriygav.github.io) | [Thesis](https://github.com/intsystems/Kiselev-BS-Thesis), [Paper 1](https://github.com/kisnikser/Posterior-Distributions-Proximity/blob/main/paper/main.pdf), [Code 1](https://github.com/kisnikser/Posterior-Distributions-Proximity/tree/main/code), [Paper 2](https://github.com/kisnikser/Likelihood-Bootstrapping/blob/main/paper/main.pdf), [Code 2](https://github.com/kisnikser/Likelihood-Bootstrapping/tree/main/code), [Slides](https://www.overleaf.com/read/gvvjjvgqhmkb#211daf) | -| Andrey Veprikov | 4 | A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Paper](https://github.com/intsystems/Veprikov-BS-Thesis/tree/master/paper), [Code](https://gitlab.com/repeated_ml/dynamic-systems-model), [Slides](https://github.com/intsystems/Veprikov-BS-Thesis/tree/master/slides) | -| Ilgam Latypov | 4 | Balancing Efficiency and Interpretability: A New Approach to Multi-Objective Optimization with High Computation Costs in Lipschitz Functions | [Dorn Y.V.](https://scholar.google.ru/citations?user=ByIc-l8AAAAJ&hl=ru) | [Paper](https://github.com/intsystems/NIR_LatypovIM/blob/main/docs/Diploma_paper.pdf), [Code](https://github.com/intsystems/NIR_LatypovIM/tree/main/code), [Slides](https://github.com/intsystems/NIR_LatypovIM/blob/main/docs/Diploma_presentation.pdf) | -| Anna Remizova | 4 | reducing the dimension of the space of the trainable parameters in the domain adaptation problem | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/slides) | -| Anastasia Voznyuk | 4 | Detection of machine-generated fragments based on text style change analysis | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Voznyuk-BS-Thesis/blob/master/paper/SemEval2024_Camera_Ready_Version/Leveraging_Transfer_Learning_for_Detecting_Boundaries_of_Machine-Generated_Texts.pdf), [Code](https://github.com/intsystems/Voznyuk-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Voznyuk-BS-Thesis/tree/master/slides/2024_5_18_NIR_Report.pdf) | -| Dorin Daniil | 4 | Spatial-temporal characteristics in the time series decoding | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/DorinDaniil/Forecasting-fMRI-Images/blob/main/paper/main.pdf), [Code 1](https://github.com/DorinDaniil/Forecasting-fMRI-Images/blob/main/code/main.ipynb), [Paper 2](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/paper/main.pdf), [Code 2](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/code/main.ipynb), [Slides](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/slides/slides.pdf) | -| Semkin Kirill | 4 | Tensor decomposition and forecast for multidimensional time series | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/intsystems/tssa_method/blob/master/doc/Tensor_SSA_Semkin.pdf), [Code](https://github.com/intsystems/tssa_method/tree/master/src), [Slides](https://github.com/intsystems/tssa_method/blob/master/doc/slides/Slides.pdf) | -| Nikitina Maria | 4 | Analysis of distribution bias in contrastive learning| [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/intsystems/Nikitina-BS-Thesis/blob/master/paper/NikitinaPaper.pdf), [Code](https://github.com/intsystems/Nikitina-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Nikitina-BS-Thesis/tree/master/slides) | -| Babkin Petr | 4 | Differential Neural Ensemble Search with Diversity Control| [Bakhteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Oleg_Bakhteev) | [Paper](https://github.com/intsystems/2023-Project-120/blob/master/paper/EdgeNES.pdf), [Code](https://github.com/intsystems/2023-Project-120/tree/master/code), [Slides](https://github.com/intsystems/2023-Project-120/blob/master/slides/slides_1.pdf) | -| Ignashin Igor | 4 | Bayesian distillation of transformer-based models | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/paper/Paper_Bayesian_distilation_Ignashin_BS_Thesis%20(5).pdf), [Code](https://github.com/intsystems/Ignashin-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Ignashin-BS-Thesis/tree/master/slides) | -| Terentyev Alexander | 4 | Classification of trajectories of dynamic systems using physically-informed neural networks | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/intsystems/Terentev-BS-Thesis/blob/master/paper/LNN_Classificator.pdf), [Code](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/slides/Slides.pdf) | -| Matvei Kreinin | 4 | Methods with preconditioning and weight decaying | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/paper.pdf), [Code](https://github.com/intsystems/Kreinin-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/slides/slides.pdf) | -| Alexander Bogdanov | 4 | Application of zero-order stochastic approximation with memoization technique in the Frank-Wolfe algorithm | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/paper/BachelorThesis_paper.pdf), [Code](https://github.com/intsystems/Bogdanov-BS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/slides/BachelorThesis_slides.pdf) | -| Okhotnikov Nikita | 4 | Interconnected latent representations for outfit generation task | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/Wayfarer123/BS_Thesis/blob/main/paper/main.pdf), [Code](https://github.com/intsystems/Okhotnikov-BS-Thesis/tree/main/code), [Slides](https://github.com/Wayfarer123/BS_Thesis/blob/main/slides/slides.pdf)| -| Oleinik Mikhail | 4 | Knowledge distillation in deep neural networks using model structure alignment methods |[Bakhteev O.Y.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) | [Paper](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Oleinik-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/slides/main.pdf) | - -### 2023 FALL - -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Viktor Pankratov | 1 | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/PankratovPHD2023/blob/main/paper/Pankratov_MS_Thesis.pdf),[Code](https://github.com/intsystems/PankratovPHD2023/tree/main/code),[Slides](https://github.com/intsystems/PankratovPHD2023/blob/main/slides/PankratovAut2023Slides.pdf) | -| Pavel Severilov | 2 | Decoding of multimodal signals of brain activity | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/severilov/phd-thesis/blob/main/report/phd_thesis.pdf), [Code](https://github.com/severilov/phd-thesis), [Slides](https://github.com/severilov/phd-thesis/tree/main/slides)| -| Alexey Grishanov | 2 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper 1](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Paper 2 - under review](), [Code](https://github.com/intsystems/GrishanovPHD2022/tree/main/code), [Slides](https://github.com/intsystems/GrishanovPHD2022/blob/main/slides/Grishanov%20DDPG%20(RL%20for%20online%20recsys).pdf) | -| Novitskii Vasilii | 3 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization| [Gasnikov A.V.](https://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Paper 3](https://proceedings.mlr.press/v162/gasnikov22a.html), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing) | -| Vasiliy Alekseev | 4 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Conf1](https://www.youtube.com/live/EdhnmkhkUiQ?feature=shared&t=6980) ([Slides1](http://www.machinelearning.ru/wiki/images/d/d4/Determination_of_the_Number_of_Topics_Intrinsically_Is_It_Possible.pdf)), [Slides2](http://www.machinelearning.ru/wiki/images/0/05/TopicBank._Collection_of_Coherent_Topics_Using_Multiple_Model_Training_with_Their_Further_Use_for_Topic_Model_Validation.pdf) | -| Tikhonov Denis | 2 | Dimensionality reduction of tensor phase spaces in nonlinear dynamical system reconstruction | [Strijov V.V.](http://www.ccas.ru/strijov/) | ([Slides](https://github.com/Denis-Tihonov/TensorDynamic/blob/main/slides/Tikhonov2024Tensors.pdf)), [Code](https://github.com/Denis-Tihonov/TensorDynamic/tree/main/code) | -| Panchenko Sviatoslav | 2 | Graph Diffusion models for human brain activity decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoPaper1Translated.pdf), [Slides](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoPaper2Slides.pdf), [Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code) | - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Rustem Islamov | 2 | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Paper](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Paper/Islamov2023MasterThesis.pdf), [Code](https://github.com/intsystems/Islamov-MS-Thesis/tree/main/Code), [Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf) | -| Kovaleva Maria | 2 | Addition of global information for enhancement of local embeddings for transactional data models | [Zaytsev A.A](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/MarKovka20/masters_nir/blob/main/thesis.pdf), [Slides](https://github.com/MarKovka20/masters_nir/blob/main/nir_preso.pdf) | -| Tolmachev Alexander | 2 | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Paper](https://openreview.net/forum?id=huGECz8dPp), [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Report.pdf) | -| Klypa Roman | 2 | Generative modeling for protein structure and interactions | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/) | [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/slides_nir2023fall.pdf), [Code](https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/multi-partner-diff)| -| Polina Barabanshchikova | 2 | Tverberg type theorems | [Polyanskii A.A.](http://polyanskii.com/)| [Paper](https://www.sciencedirect.com/science/article/pii/S0012365X23003801?via%3Dihub), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_Tverberg.pdf) -| Konstantin Yakovlev | 2 | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/paper/HPO.pdf), [Slides](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/slides/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/HyperOpt/tree/main) -| Grigoriy Ksenofontov | 2 | Adversarial Schrödinger Bridges | [Roman Isachenko]() | [Code](https://github.com/gregkseno/master-thesis), [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/3d/3d%20term.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/main.tex) | -| Alkin Emil | 2 | Expressive Power of Recurrent Neural Networks, II | [Ivan Oseledets](https://faculty.skoltech.ru/people/ivanoseledets) |[Draft](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/tensors_strong_hyp_sketch.pdf), [Slides](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/Slides(S11).pdf), [Code](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/ExpressivePowerOfRNN(S11).ipynb) | - -#### First Year Master Students - -| Student | Year | Topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Yakovlev Konstantin | 1 | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/e0695bf94256170ceb6e2860815b1f45bea950eb/paper/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/Concord-NAS/tree/rnn), [Slides](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/rnn/slides/main.pdf) | -| Galina Boeva | 1 | Identifying the relationship between labels using an attention-based algorithm for the Next Basket Recommendation task | [Zaytsev A.A](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/Gaechka777/Temporal_sets/tree/main/paper) [Code](https://github.com/Gaechka777/Temporal_sets/tree/main) [Slides](https://github.com/Gaechka777/Temporal_sets/tree/main/slides)| -| Bair Mikhailov | 1 | Undersampled MRI Reconstruction | [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Slides](https://github.com/intsystems/MRI_Reconstruction/blob/master/slides/slides.pdf)| -| Pavel Bartenev | 1 | MRI data augmentation via conditional generative 3D inpainting | [Maxim Sharaev](https://faculty.skoltech.ru/people/msharaev) | [Slides](https://github.com/intsystems/MRI-Inpainting/tree/master/slides) [Code](https://github.com/intsystems/MRI-Inpainting/tree/master/code)| -| Kseniia Petrushina | 1 | Detection of hallucinations of language models | [Alexander Panchenko](https://msc.skoltech.ru/alexanderpanchenko) | [Slides](https://github.com/intsystems/Petrushina_2024_NIR/blob/сonsistency/slides/Consistency2023Slides.pdf) [Code](https://github.com/intsystems/Petrushina_2024_NIR/tree/сonsistency/code) | -| Arina Chumachenko | 1 | Machine learning methods for functional brain mapping | [Maxim Sharaev](https://msc.skoltech.ru/maxim-sharaev) | [Slides](https://github.com/intsystems/Chumachenko_2023_NIR/blob/master/slides/Chumachenko_NIR2023.pdf) | [Code](https://github.com/intsystems/Chumachenko_2023_NIR/tree/master/code/main.ipynb) | -|Nikita Kornilov| 1 |Intermediate Gradients Methods with Relative Inexactness|Alexandr Gasnikov| [Slides](https://github.com/intsystems/Kornilov_2023_NIR/blob/master/slides/InterRel_pres_rus.pdf) [Code](https://github.com/intsystems/Kornilov_2023_NIR/blob/master/code/Numerical_exp_ISTM.ipynb) [Paper](https://github.com/intsystems/Kornilov_2023_NIR/blob/master/paper/2023_JOTA_Intermediate_Methods_with_Relative_Inexactness.pdf)| -| Dmitry Protasov | 1 | Automatic Music Transcription | Ivan Matveev | [Slides](https://github.com/Vosatorp/MusicNIR/blob/main/docs/MusicNIR_Slides.pdf) [Code](https://github.com/Vosatorp/MusicNIR/blob/main/code) [Draft](https://github.com/Vosatorp/MusicNIR/blob/main/docs/MusicNIR_Paper.pdf) | -| Parviz Karimov | 1 | Representation learning for data point groups | [Roman Isachenko](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Slides](https://github.com/intsystems/Karimov_2023_NIR/tree/master/slides) [Draft](https://github.com/intsystems/Karimov_2023_NIR/tree/master/paper) | -| Eduard Vladimirov | 1 | Adversarial attacks on neural networks for time series | [Zaytsev A.A](https://faculty.skoltech.ru/people/alexeizaitsev) | [Slides](https://github.com/intsystems/Vladimirov_2023_NIR/blob/master/slides/eavladimirov_2023_nir.pdf) [Code](https://github.com/intsystems/Vladimirov_2023_NIR/tree/master/code) [Draft](https://github.com/intsystems/Vladimirov_2023_NIR/blob/master/paper/Vladimirov_2023_paper.pdf) | -| Zharov Georgiy | 1 | Search for an effective architecture for solving the problem of obtaining multimodal embeddings for three or more modalities | | [Slides](https://github.com/Egor-s-gor/Zharov_2023_NIR/tree/main/slides) [Code](https://github.com/Egor-s-gor/Zharov_2023_NIR/tree/main/code)| - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Antyshev Tikhon | 4 | Gradient Sliding for Saddle Point problems with one composite | Gasnikov A. V. | [Code](https://github.com/intsystems/Antyshev-BS-Thesis) [Paper](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/paper/SaddleSlidingArticle.pdf) [Slides](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/slides/slides.pdf)| -| Kiselev Nikita | 4 | Bayesian Sample Size Estimation | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Kiselev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/slides/main.pdf) | -| Kreinin Matvei | 4 | On methods with preconditioning and weight decaying | [Beznosikov A. N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/kreininmv/NIR/blob/master/paper.pdf), [Code](https://github.com/kreininmv/NIR/tree/master/code), [Slides](https://github.com/kreininmv/NIR/blob/master/slides.pdf)| -| Ilgam Latypov | 4 | Research On multicriteria optimization using Shapley Value | [Dorn Y.V.](https://scholar.google.ru/citations?hl=ru&user=ByIc-l8AAAAJ&view_op=list_works&sortby=pubdate) | [Paper](https://github.com/intsystems/NIR_LatypovIM/tree/main/docs/НИР_english.pdf), [Code](https://github.com/intsystems/NIR_LatypovIM), [Slides](https://github.com/intsystems/NIR_LatypovIM/tree/main/docs/НИР_презентация.pdf)| -| Anastasiia Vozniuk | 4 | Detection of Machine-Generated Fragments in Text | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/2023-Project-126/blob/master/paper/DetectionOfFragments2023_14_12.pdf), [Code](https://github.com/intsystems/2023-Project-126/tree/master/code), [Slides](https://github.com/intsystems/2023-Project-126/blob/master/slides/2023_12_16_SlidesReport.pdf)| -| Terentyev Alexander | 4 | Classification of trajectories of dynamic systems with physics-informed neural networks | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/paper/paper.pdf), [Code](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/paper/LNN_Classificator_Slides.pdf)| -| Veprikov Andrey | 4 | A mathematical model of the hidden feedback loop effects in machine learning systems | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Paper](https://www.overleaf.com/read/whbcvrmnhgpj#914b2d), [Code](https://gitlab.com/repeated_ml/2023-project-119), [Slides](https://www.overleaf.com/read/nrhdjnjmxfqd#517273) | -| Ignashin Igor | 4 | Bayesian distilation of transformer-based models | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/paper/Paper_Bayesian_distilation_Ignashin_BS_Thesis.pdf), [Code](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/code/RNN_attention.ipynb), [Slides](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/slides/Presentation_Bayesian_distilation_Ignashin_BS_Thesis.pdf) | -| Remizova Anna | 4 | Altering latent representation in the audio style transfer task | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/AnnaRemi/BachelorThesis/tree/master/paper/Thesis_paper.pdf), [Code](https://github.com/AnnaRemi/BachelorThesis/blob/master/code/Baseline_Style_Transfer.ipynb), [Slides](https://github.com/AnnaRemi/BachelorThesis/blob/master/slides/presentation_autumn_23.pdf), [Paper handwritten draft](https://github.com/AnnaRemi/BachelorThesis/blob/master/literature/notes/thesis.pdf) | -| Babkin Petr | 4 | Differential neural ensemble search with diversity control | Bakhteev O.Y. | [Paper](https://github.com/intsystems/2023-Project-120/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/2023-Project-120/tree/master/code), [Slides](https://github.com/intsystems/2023-Project-120/blob/master/slides/slides_for_m1p.pdf) | -| Nikitina Maria | 4 | Analysis of distribution bias in contrastive learning| [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/NikitinaMaria/Contrastive_learning/blob/main/Paper/NikitinaPaper.pdf), [Code](https://github.com/NikitinaMaria/Contrastive_learning/tree/main/Code), [Slides](https://github.com/NikitinaMaria/Contrastive_learning/blob/main/Paper/Presentation/NikitinaSlides.pdf) | -| Oleinik Mikhail | 4 | Knowledge distillation in deep neural networks using model structure alignment methods |[Bakhteev O.Y.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) | [Paper](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Oleinik-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/slides/main.pdf) | -| Semkin Kirill | 4 | Tensor-SSA method in application to time series decomposition | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/sem-k32/scientific_work_Semkin/blob/master/doc/Tensor_SSA_Semkin.pdf), [Code](https://github.com/sem-k32/scientific_work_Semkin/blob/master/main_experiment.ipynb), [Slides](https://github.com/sem-k32/scientific_work_Semkin/blob/master/doc/slides/Slides.pdf) | -| Bogdanov Alexander | 4 | New Aspects of Black Box Conditional Gradient: Variance Reduction and One Point Feedback | [Beznosikov A. N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/paper/BachelorThesis_paper.pdf), [Code](https://github.com/intsystems/Bogdanov-BS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/slides/BachelorThesis_slides.pdf)| -| Dorin Daniil | 4 | Spatial-temporal characteristics in the time series decoding | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/Daniilmipt007/project_VKR/blob/master/paper/main.pdf), [Code](https://github.com/Daniilmipt007/project_VKR/blob/master/code), [Slides](https://github.com/Daniilmipt007/project_VKR/blob/master/slides/pres_NIR.pdf)| -| Okhotnikov Nikita | 4 | Interconnected latent representations for outfit generation task | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/Wayfarer123/BS_Thesis/blob/main/paper/main.pdf), [Code](https://github.com/intsystems/Okhotnikov-BS-Thesis/tree/main/code), [Slides](https://github.com/Wayfarer123/BS_Thesis/blob/main/slides/slides.pdf)| - -### 2023 SPRING - -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Pavel Severilov | 1 | Decoding of multimodal signals of brain activity | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/severilov/phd-thesis), [Slides](https://github.com/severilov/phd-thesis/tree/main/slides)| -| Grishanov Alexey | 1 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Code](https://github.com/intsystems/GrishanovPHD2022/tree/main/code), [Slides](https://github.com/intsystems/GrishanovPHD2022/blob/main/slides/Grishanov%20DDPG%20(RL%20for%20online%20recsys).pdf) | -| Panchenko Sviatoslav | 1 | Graph Diffusion Models for the Task of Signal Decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper (Translated, draft)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoArticle2023Translated.pdf), [Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code), [Slides (IDP conf.)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanhenkoIDPslides.pdf) | -| Vasilii Novitskii | 2 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing) | -| Alina Samokhina | 2 | Continous-in-time representations of signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code old](https://github.com/Alina-Samokhina/continuous_time_paper), [Paper draft](https://www.overleaf.com/read/bvrwfjgxnrjr), [Slides](https://www.overleaf.com/read/mhwjngzpfmps)| -| Vasiliy Alekseev | 3 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper (draft)](https://github.com/intsystems/2023-Project-131/blob/master/paper/Gorbulev2023TopicModels.pdf), [Slides](https://github.com/intsystems/2023-Project-131/blob/master/slides/Gorbulev2023TopicModelsPresentation.pdf) | -| Aleksei Goncharov | 4 | Space-time series alignment models | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Papers](https://scholar.google.com/citations?user=umbRPRkAAAAJ&hl=en), [Slides](https://github.com/lexix/Goncharov_PhDThesis/blob/main/Goncharov%20-%20Dissertation.pdf), [Thesis](https://www.overleaf.com/project/62b8bc7c4162ad51f49f5087) | -| Petr Ostroukhov | 4 | Tensor Methods for Convex Functions Minimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper](https://www.overleaf.com/read/ghshtbymmwym), [Slides](https://disk.yandex.ru/i/9J6zoJHwsMRwqg)| -| Denis Kuznetsov | 4 | Neural network models of dialogue on general topics | [Burtsev M.S.](https://scholar.google.ru/citations?hl=ru&user=t_PLQakAAAAJ) | [Paper with Code](https://paperswithcode.com/paper/imad-image-augmented-multi-modal-dialogue)| -| Radoslav Neychev | 4 | Informative prior in privileged learning | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Old paper](http://strijov.com/papers/Shibaev2022Symbolic.pdf), [Paper 1](https://drive.google.com/file/d/1sywZxS5bTXWPzzgUnqzgAH3QZow4BUAi/view?usp=sharing), New paper 2 (in blind review for now) | - - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Rustem Islamov | 2 | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Paper](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Paper/Islamov2023MasterThesis.pdf), [Code](https://github.com/intsystems/Islamov-MS-Thesis/tree/main/Code), [Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf) | -| Filatov Andrei | 2 | Text interfaces for event sequences | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/paper/FilatovMIPTThesis.pdf), [Slides](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/slides/FilatovMScThesisPresentation.pdf) | -| Shokorov Viacheslav | 2 | Bootstrapping of neural network ensembles | Vetrov D.P. | [Text (draft)](https://docs.google.com/document/d/1RcN3YLLUrVhFr6rNHz43iKaO3CtJeRv-D9KY7nvhWv4/edit?usp=sharing) [Slides](https://github.com/vshokorov/margin_based_ensembles_boosting/blob/main/reports/Slides_spring2023.pdf), [Code](https://github.com/vshokorov/margin_based_ensembles_boosting) | -| Safiullin Robert | 2 | Multimodel representation of dynamic systems | [Strijov V.V.](http://www.ccas.ru/strijov/)|[Paper](https://github.com/intsystems/Safiullin-MS-Thesis/blob/master/paper/master_diploma.pdf) [Slides](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/slides), [Code](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/code) | -| Bishuk Anton | 2 | Controlled Graph Generation | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Paper](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/paper/paper.pdf), [Code](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/slides/slides.pdf) | -| Pankratov Viktor | 2 | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/paper), [Code](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/slides) | -| Grebenkova Olga | 2 | Automatic detection of focal cortical dysplasia for sparse data representation | [Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) | [Draft](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/Thesis_draft.pdf), [Code](https://github.com/intsystems/Grebenkova-MS-Thesis/tree/main), [Slides](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/MSc_Thesis_PreDefence_Grebenkova.pdf) [Paper](https://www.scitepress.org/Link.aspx?doi=10.5220/0011626900003393)| -| Nadezhda Alsahanova | 2 | Selection of tensor representations for multiview forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Draft]( https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Doc/Thesis_draft.pdf), [Code](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Code/Final%20code), [Slides](https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Slides/Nadezhda_Alsahanova_SLIDES.pdf) | - -#### First Year Master Students - -| Student | Year | Topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Yakovlev Konstantin | 1 | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/e0695bf94256170ceb6e2860815b1f45bea950eb/paper/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/Concord-NAS/tree/rnn), [Slides](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/rnn/slides/main.pdf) | -| Kovaleva Maria | 1 | Neural architecture search with early stopping | [Alexey Zaytsev](https://faculty.skoltech.ru/people/alexeizaitsev) | [Code](https://github.com/MarKovka20/Project_reseach/tree/main), [Slides](https://github.com/MarKovka20/Project_reseach/blob/main/presentation.pdf), [Draft](https://docs.google.com/document/d/1A0nhXXczofwsRUDMEmy6MImaiPf9JAJ5CazqGcetn5Q/edit?usp=sharing) | -| Grigoriy Ksenofontov | 1 | Analysis of generative modeling methods based on Schrödinger bridges | [Roman Isachenko]() | [Code](https://github.com/gregkseno/master-thesis), [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/2nd/2nd%20term.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/main.tex) | -| Polina Barabanshchikova | 1 | Helly type problems for d-intervals | [Polyanskii A.A.](https://mipt.ru/education/chairs/dm/staff/polyanskii.php)| [Paper](https://arxiv.org/abs/2303.10706), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Helly%20type%20problems%20for%20d-intervals.pdf) | -| Tolmachev Alexander | 1 | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Paper](https://arxiv.org/abs/2305.08013), [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Report.pdf) | -| Alkin Emil | 1 | Expessive Power of Recurrent Neural Networks | [Oseledets I. V.](https://faculty.skoltech.ru/people/ivanoseledets) | [Slides](https://www.overleaf.com/read/bxvwpmzvnzvp), [Code](https://colab.research.google.com/drive/1mTdzgFeBJbxkDu5zR4Lw5snZ-IGUNL50?usp=sharing) | - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Antyshev Tikhon | 4 | Gradient Sliding for Saddle Point problems with one composite | Gasnikov A. V. | [Code](https://github.com/intsystems/Antyshev-BS-Thesis) [Paper](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/paper/SaddleSlidingArticle.pdf) [Slides](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/slides/slides.pdf)| -| Kornilov Nikita | 4 | Gradient Free Methods for Non-Smooth Convex Stochastic Optimization with Heavy Tails on Convex Compact | Gasnikov A. V. | [Code](https://github.com/intsystems/Kornilov-BS-Thesis/tree/main) [Paper](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/paper/gradient_free_non_smooth_heavy_tails.pdf) [Slides](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/slides/InfZero_Grad_Pres.pdf)| -| Lukyanenko Ivan | 4 | Detection of manipulations and its targets in news texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/intsystems/Lukyanenko-BS-Thesis), [Text](https://www.overleaf.com/read/zbqndyzfydpy), [Slides](https://www.overleaf.com/read/rkdykqwnvbzj)| -| Zharov Georgiy | 4 | Classification of manipulative fragments in news texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/models), [Slides](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/slides)| -| Vladimirov Eduard | 4 | Choosing a state space model in a neural decoding problem | [Strijov V.V.]([http://www.machinelearning.ru/wiki/index.php?title=User:Vokov](http://www.ccas.ru/strijov/)) | [Code1](https://github.com/Edyarich/annotated-s4), [Code2](https://github.com/Edyarich/ECGNet), [Slides](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/slides/VladimirovTSModels.pdf)| -| Molozhavenko Alexander | 4 | Solution of a block multidimensional eigenvalues search problem | Gasnikov A.V. | [Slides](https://www.overleaf.com/read/gxtnzbdhzhcj), [Code](https://github.com/intsystems/Molozhavenko-BS-Thesis) - -### 2022 AUTUMN - -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Vasiliy Alekseev | 3 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://link.springer.com/article/10.1134/S106456242202003X), [Paper (conf.)](https://link.springer.com/chapter/10.1007/978-3-031-19032-2_12) | -| Grishanov Alexey | 1 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Code](https://github.com/intsystems/GrishanovPHD2022/tree/main/code), [Slides (Sber AI Lab seminar)](https://github.com/intsystems/GrishanovPHD2022/blob/main/paper/sber_ai_lab_seminar.pdf) | -| Panchenko Sviatoslav | 1 | Graph Diffusion Models for the Task of Signal Decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper (Article, draft)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/Panchenko2022ArticleDraft.pdf), [Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code), [Slides (IDP conf.)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanhenkoIDPslides.pdf) | -| Denis | 1 | Dimension reduction of tensor phase spaces in dynamical system simulation | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Denis-Tihonov/MsThesis/blob/main/Paper/2022Classification_rus.pdf), Code, [Slides](https://github.com/Denis-Tihonov/MsThesis/blob/main/Slides/Tikhonov2022ClassificationPresentation.pdf) | -| Alina Samokhina | 2 | Continous-in-time representations of signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code old](https://github.com/Alina-Samokhina/continuous_time_paper), [Paper published](http://www.ipiran.ru/journal_system/article/08696527220304.html), [Paper draft](https://www.overleaf.com/read/fcwdwfkhthnv), [Slides](https://www.overleaf.com/read/mhwjngzpfmps)| -| Vasilii Novitskii | 2 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing)| -| Polina Potapova | 3 | Topic modeling for multilingual topic search | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://www.overleaf.com/7641677752mmzmcfghzydj), [Code](https://github.com/machine-intelligence-laboratory/text_categorization)| -| | | | | | - - - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Andrei Filatov | 2 | Infinite transformers | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Filatov-MS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Filatov-MS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Filatov-MS-Thesis/tree/master/slides) | -| Rustem Islamov | 2 | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Paper](https://arxiv.org/abs/2206.03588), [Code](https://github.com/intsystems/Islamov-MS-Thesis/tree/main/Code), [Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf) | -| Bishuk Anton | 2 | Controlled Graph Generation | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Paper](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/paper), [Code](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/slides) | -| Grebenkova Olga | 2 | Automated detection of focal cortical dysplasia |[Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) |[Slides](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/Slides_22.pdf) [Acceptance letter](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/AcceptanceLetter.pdf)| -| Safiullin Robert | 2 | Multimodel representation of dynamic systems |[Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://www.mdpi.com/2227-9040/10/12/520), [Code](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/slides) | -| Shokorov Viacheslav | 2 | Deep ensembles bootstrapping | Vetrov D.P. | [Notes](https://github.com/vshokorov/margin_based_ensembles_boosting/issues/5), [Code](https://github.com/vshokorov/margin_based_ensembles_boosting) | -| Pankratov Viktor | 2 | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/paper), [Code](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/slides) | -| Alsahanova Nadezhda | 2 | Selection of tensor representations for multiview forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Doc), [Code](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Code), [Slides](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Slides) | - -#### First Year Master Students - -| Student | Year | Topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Maria Kovaleva | 1 | Research of efficient transformers | [Alexey Zaytsev](https://faculty.skoltech.ru/people/alexeizaitsev)| [Paper](https://github.com/MarKovka20/Models-of-sequential-data-project/blob/main/literature_review.pdf), [Code](https://github.com/MarKovka20/Models-of-sequential-data-project), [Slides](https://github.com/MarKovka20/Models-of-sequential-data-project/blob/main/slides.pdf)| -| Roman Klypa | 1 | Combination of geometrical learning and language models for bioinformatics | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/)| [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/report.pdf) | -| Polina Barabanshchikova | 1 | Helly type problems for d-intervals | [Polyanskii A.A.](https://mipt.ru/education/chairs/dm/staff/polyanskii.php)| [Paper](https://github.com/pollinab/MasterThesis/blob/main/Maximum_spanning_tree.pdf), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_spanning_tree.pdf) | -| Grigoriy Ksenofontov | 1 | Creating a personalized avatar of a person for a virtual fitting of clothes | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov), Yanina A.O. | [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/1st/1st%20term.pdf) | -| Yakovlev Konstantin | 1 | Concordant Neural Architecture Search on multi-domain data | [Bakhteev O.Y.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) | [Slides](https://github.com/Konstantin-Iakovlev/Slides/raw/main/IOI/main.pdf) | - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Eduard Vladimirov | 4 | Ways to account for data noise in a Neural ODE model | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Vladimirov-BS-Thesis/raw/master/paper/VladimirovNODEandNoise.pdf), [Code](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/code/main.ipynb), [Slides](https://github.com/intsystems/Vladimirov-BS-Thesis/raw/master/slides/VladimirovNODEandNoiseSlides.pdf) | -| Antyshev Tikhon | 4 | Zero-order Mirror Descent for Saddle Point Problems | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru) | [Paper](https://github.com/intsystems/Antyshev-Zero-order-methods-for-SP/tree/master/paper), [Code](https://github.com/intsystems/Antyshev-Zero-order-methods-for-SP), [Slides](https://github.com/intsystems/Antyshev-Zero-order-methods-for-SP/tree/master/slides) | -| Ivan Lukyanenko | 4 | Joint NER and RE in manipulation news | Vorontsov K.V. | [Code](https://github.com/AlexeyVatolin/manipulation) [Slides](https://ru.overleaf.com/read/tzjhtywnzvvr) | -| Kornilov Nikita | 4 | Gradient Free Optimization with Infinite Variance | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Paper](https://github.com/Jhomanik/KornilovBSThesis/blob/main/paper/GradFree_with_inf__noise.pdf), [Slides](https://github.com/Jhomanik/KornilovBSThesis/blob/main/slides/InfZero_Grad_Pres.pdf) | -| Georgiy Zharov | 4 | Search for manipulations and their relations with named entities in texts | Vorontsov K.V. | [Slides](https://drive.google.com/file/d/1oYjCU8GJPjGBfe2d_tHbeBHT1WyB8R5i/view?usp=share_link) | -| Molozhavenko Alexander | 4 | Solution of a block multidimensional eigenvalues search problem | Gasnikov A.V. | [Slides](https://www.overleaf.com/read/gxtnzbdhzhcj), [Code](https://github.com/SuperCrabLover/BachelorDiploma) - - -### 2022 SPRING - -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Andrey Grabovoy | 1 | Bayesian Distilation | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/andriygav/PhDThesis), [Thesis](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/35-grabovoy/ds05-35-grabovoy_main.pdf?90)| -| Alina Samokhina | 1 | Continous-time representation for signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/Intelligent-Systems-Phystech/Samokhina-PhD-Thesis), [Paper](https://www.overleaf.com/read/dmtgkgpnnjkg), [Slides](https://www.overleaf.com/read/yjcdsfkscykt)| -| Nikitin Filipp | 2 | Generation and selection of graph neural network models in the problem of organic chemistry | [Strijov V. V.](http://www.machinelearning.ru/wiki/index.php?title=User:Strijov) | [Code](https://github.com/FilippNikitin/Space-of-graphs-of-chemical-reactions) | -| Polina Potapova | 2 | Topic modeling for multilingual topic search | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://www.overleaf.com/9773112327qphbychmbmjp), [Code](https://github.com/machine-intelligence-laboratory/text_categorization) | -| Vasiliy Alekseev | 2 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper (not visible)](https://openreview.net/forum?id=rKZ8XbpS8ec), [Code (private)](https://github.com/machine-intelligence-laboratory/BasisConvs) | -| Ostroukhov Petr | 3 | Tensor methods for convex optimization | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Paper 1](http://crm.ics.org.ru/journal/article/3189/), [Paper 2](http://crm.ics.org.ru/journal/article/3190/) | -| Kamil Safin | 3 | Combined methods for text plagiarism detection | Chehovich Y.V. | [Paper](https://ispranproceedings.elpub.ru/jour/article/view/1501/1320)| -| Denis Kuznetsov | 3 | Neural network models of dialogue on general topics | [Burtsev M.S.](https://scholar.google.ru/citations?hl=ru&user=t_PLQakAAAAJ) | [Paper_1](https://drive.google.com/file/d/17PLgv8CTQvC0BkJq53Ct1t509lwVepUV/view?usp=sharing), [Paper_2](https://drive.google.com/file/d/1Gg1NUpwNLz42O0Zqp9JyPBSjI0ApzVYg/view?usp=sharing)| -| Ilia Zharikov | 4 | Neural network methods for document image recognition | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/MIL-Compression-Team/QuantInit/blob/dev/docs/Paper.pdf), [Code](https://github.com/MIL-Compression-Team/QuantInit), [Slides](https://github.com/MIL-Compression-Team/QuantInit/blob/dev/docs/Slides.pdf) | -| Alex Goncharov | 3 | Space-time series alignment models | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Papers](https://scholar.google.com/citations?user=umbRPRkAAAAJ&hl=en), [Slides](https://github.com/lexix/Goncharov_PhDThesis/blob/main/Goncharov%20-%20Dissertation.pdf) | - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Petr Mokrov | 2 | Wasserstein gradient flows: modeling and applications | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ&hl=en) | [Paper](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/blob/master/paper/Mokrov2022_master_thesis.pdf), [Code](https://github.com/PetrMokrov/Large-Scale-Wasserstein-Gradient-Flows), [Slides](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/blob/master/slides/Mokrov2022_ms_defense_presentation.pdf) | -| Denis Tikhonov | 2 | Quasiperiodic time signals classification with spherical harmonics | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Denis-Tihonov/MsThesis/blob/main/Paper/Tikhonov2022Classification_rus.pdf), Code, [Slides](https://github.com/Denis-Tihonov/MsThesis/blob/main/Slides/Tikhonov2022ClassificationPresentation.pdf) | -| Natalia Varenik | 2 | Building a connectivity map of functional groups in the problem of decoding brain signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/paper/Varenik2022master_thesis.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/tree/master/code), [Slides](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/slides/master_thesis_presentation.pdf) | -| Alexey Grigorev | 2 | Regularization of neural layer via construction of frame in parameter space | [Gneushev A.N.](https://scholar.google.com/citations?hl=en&user=sjlY2q8AAAAJ) | [Slides](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/slides.pdf), [Code](https://github.com/formica-rufa/WO), [Paper](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/thesis.pdf) | -| Kolesov Aleksandr | 2 | Adverasrial method for Transfer Learning based on Optimal Transport | [Bakhteev O.Y](https://scholar.google.ru/citations?hl=ru&user=7eWNuFkAAAAJ&view_op=list_works&sortby=pubdate) | [Paper](https://github.com/Kolessov/Optimal-Transfer-Learning/blob/main/Diplome_pre.pdf), [Code](https://github.com/Kolessov/Optimal-Transfer-Learning), [Slides]( https://github.com/Kolessov/Optimal-Transfer-Learning/blob/main/Presentation.pdf) | -|Severilov Pavel | 2 | Choosing the optimal model in the problem of modeling dynamics of a physical system by neural networks | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/severilov/master-thesis/blob/main/doc/Severilov2022MasterThesis_rus.pdf) [Slides](https://github.com/severilov/master-thesis/blob/main/pres/Severilov2022MasterThesisPres.pdf) [Code](https://github.com/severilov/master-thesis/tree/main/code) [Paper2](http://crm.ics.org.ru/uploads/crmissues/crm_2022_02/2022_02_10.pdf)| -|Panchenko Sviatoslav | 2 | Bilinearity of geometric product for the task of signal decoding| [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/paper/Panchenko2022MasterThesis.pdf), [Slides](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/slides/Panchenko2022MasterPresentation.pdf) [Code](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/tree/main/code)| -|Grishanov Alexey | 2 | Application of Reinforcement Learning for recommendation system personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/shashist/master_thesis/blob/main/Grishanov2022Thesis.pdf), [Slides](https://drive.google.com/file/d/1AKAz5hTMEd0ig9ob_WvJwluz0O5Zk0A2/view?usp=sharing), [Сode](https://github.com/AILab-MLTools/RePlay)| - -#### First Year Master Students - -| Student | Year | Topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Rustem Islamov | 1 | Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning | [Richtarik P.](https://richtarik.org/), [Strijov V.V.](http://strijov.com/papers_en.html) | [Paper](https://proceedings.mlr.press/v151/qian22a.html), [Code](https://github.com/Intelligent-Systems-Phystech/Islamov-MS-Thesis/tree/master/Code), [Slides](https://github.com/Intelligent-Systems-Phystech/Islamov-MS-Thesis/blob/master/Presentation/Islamov-MS-Presentation-2022.pdf) | -| Bishuk Anton | 1 | Controlled graph generation using the variational autoencoder model |[Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q)|[Report](https://github.com/Intelligent-Systems-Phystech/Bishuk-MS-Thesis-public/blob/master/abstract.pdf)| -| Grebenkova Olga | 1 | Automated detection of focal cortical dysplasia |[Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) |[Report](https://github.com/Intelligent-Systems-Phystech/Grebenkova-MS-Thesis-public/blob/master/Report_22.pdf) | -| Filatov Andrei | 1 | Novel view synthesis|Lempitsky Victor |[Slides](https://github.com/Intelligent-Systems-Phystech/Filatov-MS-Thesis/blob/master/FilatovAndreiS10.pdf) [Code](https://github.com/Intelligent-Systems-Phystech/Filatov-MS-Thesis) | -| Safiullin Robert | 1 | Multimodel representation of dynamic systems | [Strijov V.V.](http://www.ccas.ru/strijov/) |[Paper](https://github.com/Intelligent-Systems-Phystech/Safiullin-MS-Thesis/blob/master/Paper/readme.md), [Code](https://github.com/Intelligent-Systems-Phystech/Safiullin-MS-Thesis/blob/master/code/code.ipynb), [Slides](https://github.com/Intelligent-Systems-Phystech/Safiullin-MS-Thesis/blob/master/slides/SafiullinMS_slides_2.pdf)| -| Pankratov Viktor | 1 | Topic balancing of topic models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/Intelligent-Systems-Phystech/Pankratov-MS-Thesis/blob/main/%D0%9D%D0%98%D0%A0_%D0%92%D0%B5%D1%81%D0%BD%D0%B02022_%D0%BA%D0%BE%D0%B4.ipynb), [Slides](https://github.com/Intelligent-Systems-Phystech/Pankratov-MS-Thesis/blob/main/slides_spring_2022.pdf)| -| Shokorov Viacheslav | 1 | Bootstrapping of neural network ensembles |Vetrov D.P.|[Report](https://github.com/vshokorov/power_laws_deep_ensembles/blob/main/reports/VKR_maga_v1.pdf) [Code](https://github.com/vshokorov/power_laws_deep_ensembles)| - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -|Mariya Gorpinich|4| Metaparameter optimization in knowledge distillation | Bakhteev O.Yu. | [Code](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis), [Slides](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/slides/Gorpinich2021DistillingKnowledge_slides.pdf), [Paper](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/Gorpinich2021DistillingKnowledge.pdf)| -|Vyacheslav Gorchakov|4| Importance Sampling Approach to Chance-Constrained DC Optimal Power Flow | Maximov Y.V. |[Paper](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/Gorchakov_BS_Thesis_text.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/tree/master/code), [Slides](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/BS_thesis_slides.pdf)| -|Antonina Kurdyukova|4| Dimensionality reduction of the phase space in canonical correlation analisys | Strijov V.V., Isachenko R.V. | [Code](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/blob/master/code/ccm_accelerometer.ipynb), [Slides](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/blob/master/slides/BSThesis_Kurdyukova_Slides.pdf), [Paper](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/blob/master/docs/BSThesis_Kurdyukova__Copy_-3.pdf)| -| Anton Pilkevich | 4 | Optimization of the criterion given by the neural network model in the text detoxification task | [Strijov V.V.](http://www.ccas.ru/strijov/) (Popov A.S.) |[Code](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis), [Slides](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/pres.pdf),[Paper](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/main.pdf)| -|Konstantin Yakovlev|4| Selection of concordant architectures with complexity control | Bakhteev O.Y. | [Paper](https://easychair.org/publications/preprint_open/H5MC) [Code](https://github.com/Intelligent-Systems-Phystech/DARTS-CC), [Slides](https://github.com/Intelligent-Systems-Phystech/Yakovlev-BS-Thesis/raw/master/slides/main.pdf)| -|Khristolyubov Maxim|4| Approximation of the phase trajectory of the time series | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/blob/main/paper/Khristolyubov_Bacalavr_Thesis%20(21).pdf) [Code](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/tree/main/code), [Slides](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/tree/main/slides)| - -### 2021 FALL - -#### Postgraduate Students - -| Postgraduate student | Year | PhD thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Andrey Grabovoy | 1 | A prior distribution of parameters in problems of choosing deep learning models | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/andriygav/PhDThesis/blob/master/thesis/Grabovoy2021PhDThesis.pdf), [Code](https://github.com/andriygav/PhDThesis), [Slides](https://github.com/andriygav/PhDThesis/blob/master/slides/Grabovoy2021PhDSlides.pdf)| -| Alina Samokhina | 1 | Continuous time representation for signal decoding| [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://www.overleaf.com/read/dmtgkgpnnjkg)| -| Tamaz Gadaev | 1 | Multilinear model choice in forecasting problem| [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://www.overleaf.com/read/bfrhvjqybbqw)| -| Vasilii Novitskii | 1 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing)| -| Vasiliy Alekseev | 2 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://www.sciencedirect.com/science/article/pii/S0169023X21000483), [Code](https://github.com/machine-intelligence-laboratory/OptimalNumberOfTopics), [Slides1](http://www.machinelearning.ru/wiki/images/f/fa/Alekseev2021TopicBankMMROSlides.pdf), [Slides2](http://www.machinelearning.ru/wiki/images/2/29/Alekseev2021TopicBankMIPTSlides.pdf) | -| Polina Potapova | 2 | Topic modeling for multilingual topic search | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/Guince/PhDReports/blob/main/Neuroclustering.pdf) | -| Petr Ostroukhov | 3 | Tensor methods for optimization of convex functions | [Gasnikov A.V.](https://scholar.google.ru/citations?hl=ru&authuser=1&user=AmeE8qkAAAAJ) | [Paper](https://arxiv.org/abs/2012.15595) | -| Denis Kuznetsov | 3 | Neural network models of dialogue on general topics | [Burtsev M.S.](https://scholar.google.ru/citations?hl=ru&user=t_PLQakAAAAJ) | [Paper](https://aclanthology.org/2021.codi-main.4/)| -| Kamil Safin | 3 | Intrinsic methods for plagiarised texts detection| Chehovich Y.V. | [Paper](https://link.springer.com/chapter/10.1007/978-3-030-92711-0_7)| -| Ilia Zharikov | 4 | Neural network methods for document image recognition | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | Paper | - - -#### Second Year Master Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Petr Mokrov | 2 | Wasserstein gradient flows: modeling and applications | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ&hl=en) | [Paper](https://openreview.net/forum?id=nlLjIuHsMHp), [Code](https://github.com/PetrMokrov/Large-Scale-Wasserstein-Gradient-Flows), [Slides](https://drive.google.com/file/d/1t0lYIeBDujZLmkbtXqwLe-_nkOKf6kzj/view?usp=sharing) | -| Denis Tikhonov | 2 | Model selection for quasiperiodic time series forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) |[Code](https://github.com/Denis-Tihonov/Spherical_Harmonics_parametrisation), [Slides](https://github.com/Denis-Tihonov/Spherical_Harmonics_parametrisation/blob/main/slides/Tikhonov2021ApproximatinPresentation.pdf)| -| Alexey Grigorev | 2 | Regularization of neural layer via construction of frame in parameter space | [Gneushev A.N.](https://scholar.google.com/citations?hl=en&user=sjlY2q8AAAAJ) | [Slides](https://drive.google.com/uc?id=19rg9DegVH_rQRsjpasatkpMCMpha3kDt&export=download), [Code](https://github.com/formica-rufa/WO); [Paper](https://drive.google.com/uc?id=1lVVXaKIkzWixxp8KK-imWGnvt0JDt1Is&export=download) | -|Natalia Varenik| 2 | Building a connectivity map of functional groups in the problem of decoding brain signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Natalia-Varenik/MasterThesis/blob/main/doc/Graphs_for_BCI-5.pdf) [Slides](https://github.com/Natalia-Varenik/MasterThesis/blob/main/slides/master_thesis_presentation.pdf) [Code](https://github.com/Natalia-Varenik/MasterThesis/tree/main/code)| -|Severilov Pavel | 2 | Differential analysis of phase spaces in the problem of decoding signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Slides](https://github.com/severilov/master-thesis/blob/main/pres/Severilov2022MasterThesisPres.pdf) [Code](https://github.com/severilov/master-thesis/tree/main/code)| -|Panchenko Sviatoslav | 2 | Bilinearity of geometric product for the task of signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Slides](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/notes/GeometricAlgebraForDecoding.pdf)| -|Grishanov Alexey | 2 | Application of Reinforcement Learning for recommendation system personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Slides](https://drive.google.com/file/d/1AKAz5hTMEd0ig9ob_WvJwluz0O5Zk0A2/view?usp=sharing), [Сode](https://github.com/shashist/recsys-rl)| -|Kolesov Aleksandr | 2 | Adversarial approach for transfer learning | [Bahteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) |[Paper](https://drive.google.com/file/d/1wazibI5TtWUiOn3k6es5YdXasS3XeMeG/view?usp=sharing), [Slides](https://docs.google.com/presentation/d/10BEdMzxupJbj7xkb-20MPluqXQ2qTK-ojpaXmtA8E9s/edit?usp=sharing), [Сode](https://github.com/Intelligent-Systems-Phystech/HeterogenKD/tree/main/code/notebooks)| - -#### First Year Master Students - -| Student | Year | Topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Rustem Islamov|1 |Second Order Methods for Federated Learning |[Richtarik P](https://richtarik.org/), [Strijov V.V.](http://www.ccas.ru/strijov/) |[Paper](https://arxiv.org/abs/2106.02969), [Code](https://github.com/Intelligent-Systems-Phystech/Islamov-Rustem/tree/main/Master%20Thesis/Code), [Slides](https://github.com/Intelligent-Systems-Phystech/Islamov-Rustem/blob/main/Master%20Thesis/Presentation/Islamov2021Presentation.pdf) | -| Grebenkova Olga | 1 | Automated detection of focal cortical dysplasia |[Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) |[Paper](http://www.mathnet.ru/links/bf98d4af33339019591a1b13329cae49/ia710.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/VarHyperNet), [Slides](https://github.com/Intelligent-Systems-Phystech/Grebenkova-BS-Thesis/blob/main/Grebenkova2020OptimizationSlides.pdf) | -| Safiullin Robert | 1 | Substance properties analysis based on its SERS spectra | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Report](https://github.com/roberts2510/SafiullinMSThesis/blob/main/Safiullin_report.pdf), [Slides](https://github.com/roberts2510/SafiullinMSThesis/blob/main/Slides/SafiullinMS_slides_1.pdf)| -| Pankratov Viktor| 1| Topic balancing of topic models| [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Report](https://github.com/PankratovViktor/Pankratov_BS_Thesis/blob/main/Pankratov_Report_S9_2021.pdf),[Code](https://github.com/PankratovViktor/Pankratov_BS_Thesis/tree/main/pyartm)| -| Filatov Andrei| 1| Task Discovery | [Victor Lempitsky](https://faculty.skoltech.ru/people/victorlempitsky) [Strijov V.V.](http://www.ccas.ru/strijov/) |[Report](https://github.com/Intelligent-Systems-Phystech/Filatov-MS-Thesis/blob/master/FilatovAndrei(S9)2021.pdf) | -| Bishuk Anton | 1 | Controlled graph generation using the variational autoencoder model |[Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q)|[Report](https://github.com/Intelligent-Systems-Phystech/Bishuk-MS-Thesis-public/blob/master/%D0%9E%D0%B1%D0%B7%D0%BE%D1%80-%D0%BB%D0%B8%D1%82%D0%B5%D1%80%D0%B0%D1%82%D1%83%D1%80%D1%8B.pdf)| -| Shokorov Viacheslav | 1 | Bootstrapping of neural network ensembles |Vetrov D.P.|[Report](https://github.com/vshokorov/power_laws_deep_ensembles/blob/main/reports/VKR_maga_v1.pdf) [Code](https://github.com/vshokorov/power_laws_deep_ensembles)| - -#### Fourth Year Bachelor Students - -| Student | Year | Thesis topic | Scientific adviser | Link to publication | -|:---:|:---:|:---:|:---:|:---:| -| Antonina Kurdyukova | 4 | Phase detection of human motions with signals of wearable devices | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/raw/master/docs/Kurdyukova2021Phase%20(44).pdf), [Code](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/tree/master/code), [Slides](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/raw/master/slides/Kurdyukova2021Phase%20(46).pdf) | -| Anton Pilkevich | 4 | Clustering of news text messages based on polar opinions | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) || -| Gorpinich Mariya | 4 | Metaparameter optimization in knowledge distillation | [Bakhteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Oleg_Bakhteev) | [Paper](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/docs/Gorpinich2021DistillingKnowledge.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis), [Slides](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/docs/slides/Gorpinich2021DistillingKnowledgeSlides.pdf) | -| Vyacheslav Gorchakov | 4 | Importance Sampling Approach to Chance-Constrained DC Optimal Power Flow | Maximov Y.V. |[Paper](https://arxiv.org/abs/2111.11729), [Code](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/tree/master/code)| -|Konstantin Yakovlev|4| Selection of concordant architectures with complexity control | Bakhteev O.Y. | [Code](https://github.com/Intelligent-Systems-Phystech/DARTS-CC), [Slides](https://github.com/Intelligent-Systems-Phystech/Yakovlev-BS-Thesis/raw/master/slides/main.pdf)| +## Research Reports + +This page contains information about the research projects of students at the Intelligent Systems Department. Here you can find the topics of theses, names of advisors, links to publications, presentations and code repositories. + +### 2025 Spring + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :------------------- | :--: | :----------------------------------- | :---------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------ | +| Konstantin Yakovlev | 1 | Tensor Methods in Federated Learning | [Gasnikov A.V.](https://scholar.google.com/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Publication 1](https://neurips.cc/virtual/2024/poster/93240), [Publication 2](https://arxiv.org/abs/2502.13662) | +| Grigoriy Ksenofontov | 1 | Discrete Schrödinger Bridges | [Korotin A.A.](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Publication](https://arxiv.org/abs/2502.01416), [Code](https://github.com/gregkseno/csbm), [Slides](https://www.overleaf.com/read/wqycyqmzwjpw#b5787d) | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :----------------- | :--------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Nikita Kornilov | Optimal Flow Matching: Learning Straight Trajectories in Just One Step | Gasnikov A.V. | [Publication](https://proceedings.neurips.cc/paper_files/paper/2024/file/bc8f76d9caadd48f77025b1c889d2e2d-Paper-Conference.pdf), [Slides](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/slides/Kornilov%20slides%20Research.pdf), [Paper](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/paper/Kornilov_Nikita_Thesis.pdf), [Code](https://github.com/intsystems/Kornilov_2024_NIR/tree/master) | +| Galina Boeva | Efficient aggregation by labels for the problem of event sequences | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Publication](https://ebooks.iospress.nl/volumearticle/70171?_gl=1*1kzsn7p*_up*MQ..*_ga*MTE2NzcyNzQzLjE3MzM4MjMzNDE.*_ga_6N3Q0141SM*MTczMzgyMzM0MS4xLjAuMTczMzgyMzM0MS4wLjAuMA..), [Slides](https://github.com/Gaechka777/NIR24_25/blob/master/slides/slides_nir_12sem.pdf), [Paper](https://arxiv.org/abs/2303.00280), [Code](https://github.com/intsystems/Boeva-MS-Thesis) | +| Vladimirov Eduard | Generative causal inference for Brain-Computer Interfaces | Strijov V. V. | [Paper](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/paper/Vladimirov2024GenerativeCIPaper.pdf), [Slides](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/slides/Vladimirov2024GenerativeCISlides.pdf), [Code](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master/code) | +| Bair Mikhailov | Development of Machine Learning Methods for Radiology in Brain Evolution Research | [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Paper](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/paper/main.pdf), [Slides](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/slides/slides.pdf), [Code](https://github.com/intsystems/Mikhailov-MS-Thesis) | +| Arina Chumachenko | Preventing Overfitting in Subject-Driven Text-to-Image Diffusion: Regularization of Embedding and Attention Maps | [Oseledets I.V.](https://faculty.skoltech.ru/people/ivanoseledets) | [Paper](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/paper/MSc_Thesis_Chumachenko.pdf), [Slides](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/slides/MSc_Defense_Chumachenko.pdf), [Code](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis) | +| German Gritsai | Verification of artificially generated text fragments | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Gritsai-MS-Thesis/tree/master/paper), [Slides](https://github.com/intsystems/Gritsai-MS-Thesis/blob/master/slides/mipt_nir.pdf), [Code](https://github.com/intsystems/Gritsai-MS-Thesis/tree/master/src) | +| Ildar Khabutdinov | Исправление грамматических ошибок в домене низкоресурсных языков | [Grabovoy A.V.](https://andriygav.github.io) | [Publication](https://github.com/intsystems/masters-thesis/blob/main/SpellingCorrectionFinal.pdf), [Publication](), [Slides](https://github.com/intsystems/masters-thesis/blob/main/presentation.pdf) | +| Marat Khusainov | Understanding the Plasticity of Neural Networks Employed in GFlowNets | Samsonov S.V. | [Paper](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/paper/main.pdf), [Slides](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/slides/slides.pdf), [Code](https://github.com/intsystems/Khusainov-MS-Thesis/tree/master/code) | +| Petrushina Kseniia | Detection of Multimodal Hallucinations Based on Internal Representations and Activations of Models | [Panchenko A. I.](https://msc.skoltech.ru/alexanderpanchenko) | [Publication 1](https://aclanthology.org/2025.naacl-srw.28/) [Publication 2](https://arxiv.org/abs/2503.15948), [Slides](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/slides/Slides2025Petrushina.pdf), [Paper](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/paper/NIR2025Petrushina.pdf), [Code](https://github.com/intsystems/Petrushina-MS-Thesis/tree/master/code) | + +#### Master's Students (1st year) + +| Student | Thesis topic | Advisor | Links | +| :------------------ | :----------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Dorin Daniil | Enhancing fMRI Data Decoding with Spatiotemporal Characteristics in Limited Dataset | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://drive.google.com/file/d/1lwVA3lI0CHYr8JWr9bBvvv9ZkaZdbNvf/view?usp=drive_link), [Slides](https://drive.google.com/file/d/1aTMGkRvo1RFinYyP8Fcs1TkQYPMiRe6u/view?usp=sharing), [Code](https://github.com/intsystems/Spatial-and-Temporal-Characteristics) | +| Nikitina Maria | Методы векторного представления глубоких генеративных моделей | [Bakhteev O. Yu.](https://intsystems.github.io/people/bakhteev_oy/index.html) [Bishuk A. Yu.](https://intsystems.github.io/people/bishuk_ay/index.html) | [Paper](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/paper), [Code](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/code), [Slides](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/slides) | +| Latypov Ilgam | Functional multi-armed bandit and the best function identification problems | [Y.V. Dorn](https://scholar.google.com/citations?user=ByIc-l8AAAAJ&hl=ru) | [Paper](https://arxiv.org/pdf/2503.00509), [Paper Int](https://github.com/intsystems/Latypov-MS-FMAB/blob/main/paper/FMAB.pdf) [Slides](https://github.com/intsystems/Latypov-MS-FMAB/blob/main/slides/FMAB_presentation.pdf), [Code](https://github.com/intsystems/Latypov-MS-FMAB/tree/main) | +| Semkin Kirill | Time series classification approaches through NeuralODE | Strijov V.V | [Paper](https://github.com/intsystems/n_ode/blob/main/paper/node_classification_Semkin.pdf), [Code](https://github.com/intsystems/n_ode/tree/main), [Slides](https://github.com/intsystems/n_ode/blob/main/slides/neural_ode_Semkin_slides.pdf) | +| Nikita Kiselev | Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://link.springer.com/article/10.1134/S1064562424601987), [Code](https://github.com/intsystems/landscape-hessian/tree/validation/code), [Slides](https://github.com/intsystems/landscape-hessian/blob/validation/slides/main.pdf) | +| Igor Ignashin | Theory for Adaptive Loss Scaling | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Ignashin_MS_thesis/blob/master/paper/_NIPS__Proof_for_ALSO-2.pdf), [Code](https://github.com/intsystems/Ignashin_MS_thesis/tree/master/code), [Slides]() | +| Andrey Veprikov | Оптимальное управление в системах машинного обучения с обратной связью: предотвращение деградации и оттока пользователей | [Khritankov A.S.](https://scholar.google.com/citations?user=OtxWKpMAAAAJ&hl=en) | [Paper](https://github.com/intsystems/Veprikov-MS-Thesis/blob/main/paper/%D0%A2%D0%B5%D0%B7%D0%B8%D1%81%D1%8B%20%D0%92%D0%B5%D0%BF%D1%80%D0%B8%D0%BA%D0%BE%D0%B2.pdf), [Code](https://github.com/intsystems/Veprikov-MS-Thesis/tree/main/dynamic-systems-model), [Slides](https://github.com/intsystems/Veprikov-MS-Thesis/blob/main/slides/67_%D0%BA%D0%BE%D0%BD%D1%84%D0%B5%D1%80%D0%B5%D0%BD%D1%86%D0%B8%D1%8F_%D0%9C%D0%A4%D0%A2%D0%98.pdf) | +| Okhotnikov Nikita | Low rank attention denoising | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/LowRankAttentionDenoising/blob/main/paper/main.pdf), [Slides](https://github.com/intsystems/LowRankAttentionDenoising/tree/main/slides), [Code](https://github.com/intsystems/LowRankAttentionDenoising/tree/main/code/adapter) | +| Voznyuk Anastasia | Анализ внутренних представлений языковых моделей для поиска сгенерированных документов | [Grabovoy A.V.](https://andriygav.github.io) | [Paper 1](https://arxiv.org/pdf/2503.03601), [Paper 2](https://github.com/intsystems/Internal_States_Level_MachineGen_NIR/blob/main/paper/m1p.pdf) [Code](https://github.com/intsystems/Internal_States_Level_MachineGen_NIR/tree/main/code), [Slides](https://github.com/intsystems/Internal_States_Level_MachineGen_NIR/blob/main/slides/16_05_2024_NIR_Report.pdf) | +| Terentyev Alexander | Inverse problems in modeling neural partial differential equations | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/intsystems/Terentyev-MS-InPDE/blob/main/paper/Inverse_nPDE__Paper_.pdf), [Code](https://github.com/intsystems/Terentyev-MS-InPDE/tree/main/experiments/base), [Slides](https://github.com/intsystems/Terentyev-MS-InPDE/blob/main/slides/Inverse_problems_in_modeling_neural_partial_differential_equations_Slides.pdf) | +| Babkin Petr | Position Informed Convolution for Multi-Agent Computer Vision | Shubin N.Y. | [Paper](https://github.com/intsystems/position-informed-convolution/blob/main/assets/PIC.pdf), [Code](https://github.com/intsystems/position-informed-convolution/tree/main/code), [Slides](https://github.com/intsystems/position-informed-convolution/blob/main/assets/PIC_slides.pdf) | +| Nasyrov Ruslan | Marked Temporal Point Process with Neural ODE | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](), [Code](https://github.com/intsystems/DM-TPP-with-Neural-ODE/tree/master/code), [Slides](https://github.com/intsystems/DM-TPP-with-Neural-ODE/blob/master/slides/DM_TPP_presentation.pdf) | +| Kreinin Matvei | Нормализирующие потоки для перевода КТ изображений | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Kreinin-MS-Thesis/blob/main/paper/paper_xFlow.pdf), [Code](https://github.com/intsystems/Kreinin-MS-Thesis/tree/main/src), [Slides](https://github.com/intsystems/Kreinin-MS-Thesis/blob/main/slides/slides.pdf) | +| Zabarianska Iryna | Параметрические методы решения задачи о мосте Шредингера | [Korotin A.A.](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Paper](https://github.com/Akshiira/SB-problem/blob/173f0b00060128f9e727c347778627d1467b1b5e/Abstract.pdf), [Code](https://github.com/Akshiira/SB-problem/blob/0da718188c417ba7b637efecd74980dc3e8b7bf5/Jaakkola%20Light%20SB.py), [Slides](https://github.com/Akshiira/SB-problem/blob/0da718188c417ba7b637efecd74980dc3e8b7bf5/%D0%9F%D1%80%D0%B5%D0%B7%D0%B5%D0%BD%D1%82%D0%B0%D1%86%D0%B8%D1%8F_%D0%9D%D0%98%D0%A0_6_%D1%81%D0%B5%D0%BC%D0%B5%D1%81%D1%82%D1%80.pdf) | +| Sapronov Yuri | Solving the Ranking Problem Using Continuous Optimization Methods | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ) | [Paper](https://github.com/intsystems/LtR_intsys/blob/main/paper.pdf), [Code](https://github.com/intsystems/LtR_intsys/tree/main/Transformer), [Slides](https://github.com/intsystems/LtR_intsys/blob/main/report.pdf) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :-------------------- | :----------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| Firsov Sergey | Neural architecture search with target hardware control | [Bakhteev O. Y.](https://bahleg.site/publications) | [Paper](https://github.com/intsystems/Firsov_FBNet/blob/master/paper/main_paper.pdf), [Code](https://github.com/intsystems/Firsov_FBNet/tree/master/code), [Slides](https://github.com/intsystems/Firsov_FBNet/blob/master/slides/slides.pdf) | +| Zadvornov Egor | Forecasting social trends with high volatility | Malkov A. S. | [Paper](https://github.com/intsystems/Zadvornov_Egor_paper/blob/master/paper/Zadvornov2024VolatilityTimeSeries.pdf), [Code](https://github.com/intsystems/Zadvornov_Egor_paper/tree/master/src), [Slides]() | +| Meshkov Vladislav | ConvNets Landscape Convergence: Hessian-Based Analysis of Matricized Networks | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks), [Slides](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/slides/main.pdf) | +| Papay Ivan | Ordinal Classification Using Partially Ordered Feature Sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/intsystems/Papay-BS-Thesis/blob/master/code/mixtures.ipynb) [Paper](https://github.com/intsystems/Papay-BS-Thesis/blob/master/paper/PartialOrders.pdf) [Slides](https://github.com/intsystems/Papay-BS-Thesis/blob/master/slides/PartialOrders_slides.pdf) | +| Nabiev Muhammadsharif | Inductive Bias in Model Selection | [Bakhteev O. Y.](https://bahleg.site/publications) | [Paper](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/IB_in_model_selection.pdf), [Code](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/analysis/symreg_circles.ipynb), [Slides](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/slides.pdf) | +| Anastasiia Linich | Топологический анализ математических доказательств, генерируемых большими языковыми моделями на формальном языке Lean4 | Barannikov S.A. | [Code](https://github.com/khilling/diploma/tree/main), [Paper](https://github.com/khilling/diploma/blob/main/srw_text.pdf), [Slides](https://github.com/khilling/diploma/blob/main/srw_presentation.pdf) | +| Rubtsov Denis | Сходимость с оценкой вероятностей больших отклонений для задач выпуклой оптимизации и седловых задач в условиях повышенной гладкости | [Gasnikov A.V.](https://ru.wikipedia.org/wiki/Гасников,_Александр_Владимирович) | [Paper](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/paper/RUBTSOV_DIPLOMA.pdf), [Code](https://github.com/intsystems/Rubtsov-BS-thesis/tree/master/code), [Slides](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/slides/Rubtsov_bachelor_diploma_slides.pdf) | +| Khafizov Fanis | Adaptive Compression in Distributed Optimization | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/slides) | +| Eynullayev Altay | Forecasting models in riemannian phase space | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/paper/paper.pdf), [Code](https://github.com/intsystems/Eynullayev-BS-Thesis/tree/master/code), [Slides]() | +| Karpeev Gleb | Порождающие модели для прогнозирования наборов временных рядов | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/intsystems/2024-Project-152/blob/master/code), [Paper](https://github.com/intsystems/2024-Project-152/blob/master/paper/diploma.pdf), [Slides](https://github.com/intsystems/2024-Project-152/blob/master/slides/presentation%20Karpeev%20latest.pdf) | +| Stepanov Ilya | Using Synthetic Data Obtained by Generative Neural Networks to Improve the Quality of Detection Models | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master/paper), [Code](https://github.com/ILIAHHne63/PaperFramework), [Slides](https://github.com/intsystems/Stepanov-BS-Thesis/blob/master/slides/main.pdf) | +| Rebrikov Alexey | Investigation of Neural Network Sparsification Mechanisms Based on Weight Importance | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/NoblFriend/bachelor-thesis/tree/IDA), [Slides](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/slides/main.pdf) | +| Fedor Sobolevsky | Application of Large Language Models for Hierarchical Summarization of Scientific Texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/intsystems/Sobolevsky-BS-Thesis/tree/main/code),[Paper](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/paper/Sobolevsky2025BSThesis.pdf), [Slides](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/slides/Sobolevsky2024Presentation.pdf) | +| Kasiuk Vadim | Application of compression operators in distributed optimization problems | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/KasiukVadim/BacDip24_25/blob/main/docs/Kasiuk2024CompressionForDistributedOptimization.pdf), [Code](https://github.com/KasiukVadim/BacDip24_25/blob/main/notebooks/MethodsNotebook.ipynb), [Slides]() | + +### 2024 Fall + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :------------------- | :--: | :----------------------------------- | :---------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Viktor Pankratov | 2 | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/PankratovPHD2024/tree/main/paper),[Code](https://github.com/intsystems/PankratovPHD2024/tree/main/code),[Slides](https://github.com/intsystems/PankratovPHD2024/tree/main/slides) | +| Konstantin Yakovlev | 1 | Tensor Methods in Federated Learning | [Gasnikov A.V.](https://scholar.google.com/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Publication 1](https://openreview.net/pdf?id=uvFDaeFR9X), [Publication 2](https://aclanthology.org/2024.findings-emnlp.345/) | +| Grigoriy Ksenofontov | 1 | Discrete Schrödinger Bridges | [Korotin A.A.](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Publication](https://openreview.net/forum?id=LikKyNlzgP), [Code](https://github.com/gregkseno/ipmf), [Slides](https://www.overleaf.com/read/jvfmrzpbdbzw#343d8d) | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :----------------- | :--------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Galina Boeva | Efficient aggregation by labels for the problem of event sequences | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Publication](https://ebooks.iospress.nl/volumearticle/70171?_gl=1*1kzsn7p*_up*MQ..*_ga*MTE2NzcyNzQzLjE3MzM4MjMzNDE.*_ga_6N3Q0141SM*MTczMzgyMzM0MS4xLjAuMTczMzgyMzM0MS4wLjAuMA..), [Paper](https://arxiv.org/abs/2303.00280), [Slides](https://github.com/Gaechka777/NIR24_25/blob/master/slides/slides_nir_11sem.pdf), [Code](https://github.com/Gaechka777/NIR24_25) | +| Nikita Kornilov | Optimal Flow Matching: Learning Straight Trajectroies in Just One Step | [Gasnikov A.V.](https://scholar.google.com/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Publication](https://openreview.net/forum?id=kqmucDKVcU), [Paper](https://github.com/Jhomanik/Optimal-Flow-Matching/blob/main/paper/Optimal_Flow_Matching_NIPS.pdf), [Slides](https://github.com/Jhomanik/Optimal-Flow-Matching/blob/main/slides/OFM_Research_Fall_2024.pdf), [Code](https://github.com/Jhomanik/Optimal-Flow-Matching/tree/main) | +| Eduard Vladimirov | Generative Causal Inference for BCI | Strijov V.V. | [Paper](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/paper/Vladimirov2024GenerativeCIPaper.pdf), [Slides](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master/slides), [Code](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master/code) | +| Arina Chumachenko | Controlled Image Editing Mechanisms Based on Diffusion Models | [Oseledets I.V.](https://scholar.google.com/citations?user=5kMqBQEAAAAJ&hl=ru) | [Paper](https://github.com/arina-chumachenko/Chumachenko_NIR2024/tree/master/paper), [Slides](https://github.com/arina-chumachenko/Chumachenko_NIR2024/tree/master/slides), [Code](https://github.com/arina-chumachenko/Chumachenko_NIR2024/tree/master/code) | +| Marat Khusainov | Understanding the plasticity of neural networks employed in GFlowNets | Samsonov S.V. | [Paper](https://github.com/maratkhusainov/NIR-main/blob/master/paper/main.pdf), [Slides](https://github.com/maratkhusainov/NIR-main/blob/master/slides/slides.pdf), [Code](https://github.com/maratkhusainov/NIR-main/tree/master/code) | +| Kseniia Petrushina | Detection of Hallucinations in Multimodal Models Based on Internal Representations | [Alexander Panchenko](https://msc.skoltech.ru/alexanderpanchenko) | [Paper](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/paper/NIR2024Petrushina.pdf), [Slides](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/slides/NIR2024Slides.pdf), [Code](https://github.com/intsystems/Petrushina_2024_NIR/tree/master/code) | +| German Gritsai | Verification of artificially generated text fragments | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/grgera/Text-detection-dataset/blob/main/nir/papers/2410.14677v1.pdf), [Paper 2](https://github.com/grgera/Text-detection-dataset/blob/main/nir/papers/2411.07343v1.pdf), [Paper 3](https://github.com/grgera/Text-detection-dataset/blob/main/nir/papers/2411.11736v1.pdf), [Slides](https://github.com/grgera/Text-detection-dataset/blob/main/nir/slides/mipt_nir-5.pdf), [Code](https://github.com/grgera/Text-detection-dataset/tree/main) | +| Ildar Khabutdinov | Исправление Грамматических Ошибок в Домене Низкоресурсных Языков | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/depinwhite/masters-thesis/blob/main/SpellingCorrectionFinal.pdf), [Paper 2](), [Slides]() | +| Bair Mikhailov | Сегментация и объяснимое машинное обучение в задачах радиологии | [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Slides](https://github.com/MikhailovBair/Mikhailov-MS-Thesis/blob/master/slides/TSR_MIkhailov_Bair.pptx), [Poster](https://github.com/MikhailovBair/Mikhailov-MS-Thesis/blob/master/slides/Mikhailov%202024.pdf), [Code](https://github.com/MikhailovBair/Mikhailov-MS-Thesis) | + +#### Master's Students (1st year) + +| Student | Topic | Advisor | Links | +| :------------------ | :---------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Nikita Kiselev | Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://arxiv.org/abs/2409.11995), [Code](https://github.com/kisnikser/landscape-hessian), [Slides](https://github.com/kisnikser/landscape-hessian/blob/main/slides/main.pdf) | +| Daniil Dorin | Декодирование визуальных стимулов из мультимодальных сигналов мозга | [Grabovoy A.V.](https://andriygav.github.io) | [Publication](https://link.springer.com/article/10.1007/s13755-024-00315-5), [Paper1](https://drive.google.com/file/d/1XD056tNYgLA3KNU5s8w6mxgR2W5tXUE-/view?usp=drive_link), [Paper2](https://drive.google.com/file/d/1Vqa48auYId8cRfX20Y4T-Irv3kLDMF3V/view?usp=sharing), [Code1](https://github.com/intsystems/CreationOfIntelligentSystems_Simultaneous_fMRI-EEG), [code2](https://github.com/DorinDaniil/Spatial-and-Temporal-Characteristics), [Slides](https://ru.overleaf.com/read/bcxqhzhdndzv#83b8ae) | +| Kirill Semkin | Time series classification in parameters space using NeuralODE | Strijov V.V. | [Paper](https://github.com/intsystems/n_ode/blob/hypothesis_exp/docs/node_classification_Semkin.pdf),[Code](https://github.com/intsystems/n_ode/tree/hypothesis_exp/experiments),[Slides](https://github.com/intsystems/n_ode/blob/hypothesis_exp/slides/neural_ode_Semkin_slides.pdf), | +| Andrey Veprikov | The optimal control problem in artificial intelligence systems with feedback loop | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Paper](https://arxiv.org/abs/2405.02726), [Code](https://gitlab.com/repeated_ml/dynamic-systems-model),[Slides](https://github.com/Vepricov/Veprikov-BS-Thesis/blob/master/slides/_Ms_2024__presentation.pdf) | +| Ilgam Latypov | γ-Competitiveness: An Approach to Multi-Objective Optimization with High Computation Costs in Lipschitz Functions | [Dorn Y.V.](https://labmmo.ru/team/dorn.html) | [Paper](https://arxiv.org/abs/2410.03023), [Publication](https://rdcu.be/elTnX), [Code](https://github.com/xxamxam/paper1), [Slides](https://www.overleaf.com/read/kxtsrvbmqcxx#bd0852) | +| Ignashin Igor | Stochastic Correspondences Frank-Wolfe | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Ignashin_MS_thesis/blob/master/paper/2024_Stochastic_Correspondence-2.pdf), [Code](https://github.com/ThunderstormXX/mmo_tm), [Slides](https://github.com/intsystems/Ignashin_MS_thesis/blob/master/slides/_NIR__Stochastic_Correspondences_Frank_Wolfe.pdf) | +| Babkin Petr | Position Informed Convolution for Multi-Agent Curve Detection | Shubin N.Y. | [Paper1](https://github.com/petr-parker/position-informed-convolution/blob/main/assets/PIC.pdf), [Code1](https://github.com/petr-parker/position-informed-convolution/tree/main/code), [Paper2](https://github.com/intsystems/2023-Project-120/blob/master/paper/main.pdf), [Code2](https://github.com/intsystems/2023-Project-120/tree/master/code), [Slides](https://github.com/petr-parker/position-informed-convolution/blob/main/assets/PIC_slides.pdf) | +| Terentyev Alexander | Inverse problems in modeling neural partial differential equations | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/lopate/lagrange_classification/blob/master/paper/SNCS-D-24-08760.pdf), [Code](https://github.com/lopate/lagrange_classification/tree/master/code), [Slides](https://github.com/lopate/inverse-npde/blob/main/slides/Inverse_problems_in_modeling_neural_partial_differential_equations_Slides.pdf) | +| Nasyrov Ruslan | Decomposition of uncertainty in neural networks | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/intsystems/uncertainty_quantification_2024/blob/master/paper/Calibration_thesis.pdf), [Code](https://github.com/intsystems/uncertainty_quantification_2024/tree/master/code), [Slides]() | +| Zabarianska Iryna | Параметрические методы решения задачи о мосте Шредингера | [Alexander Korotin](https://scholar.google.ru/citations?user=1rIIvjAAAAAJ&hl=en) | [Paper](https://arxiv.org/abs/2408.01753), [Code](https://github.com/Akshiira/-5-/blob/main/main.py), [Slides](https://github.com/Akshiira/-5-/blob/main/%D0%9F%D1%80%D0%B5%D0%B7%D0%B5%D0%BD%D1%82%D0%B0%D1%86%D0%B8%D1%8F_%D0%9D%D0%98%D0%A0_5_%D1%81%D0%B5%D0%BC%D0%B5%D1%81%D1%82%D1%80.pdf) | +| Nikitina Maria | Методы векторного представления глубоких генеративных моделей | [Bakhteev O. Yu.](https://intsystems.github.io/people/bakhteev_oy/index.html) [Bishuk A. Yu.](https://intsystems.github.io/people/bishuk_ay/index.html) | [Paper](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/paper), [Code](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/code), [Slides](https://github.com/intsystems/Vector-space-of-generative-models/tree/master/slides) | +| Kreinin Matvei | Генерация обучающей выборки с помощью ограниченного набора данных | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/kreininmv/Pseudo-labeling/blob/master/src/article/article.pdf), [Code](https://github.com/kreininmv/Pseudo-labeling/tree/master/experiments), [Slides](https://github.com/kreininmv/Pseudo-labeling/blob/master/src/slides/slides.pdf) | +| Sapronov Yuri | Solving the ranking problem with continuous optimization methods | [Gasnikov A. V.](https://www.hse.ru/org/persons/49503846/) | [Paper](https://github.com/Sapr7/Learning-To-Rank/blob/sapr/icml2025.pdf), [Code](https://github.com/Sapr7/Learning-To-Rank/tree/bobr), [Slides](https://github.com/Sapr7/Learning-To-Rank/blob/sapr/%D0%9D%D0%98%D0%A0_presentation.pdf) | +| Voznyuk Anastasia | Анализ неопределенности и внутренних представлений языковых моделей для поиска сгенерированных документов | [Grabovoy A.V.](https://andriygav.github.io) | [Paper 1](https://arxiv.org/abs/2410.14677), [Paper 2](https://arxiv.org/abs/2410.02343), [Paper 3](https://arxiv.org/abs/2411.11736), [Code](https://github.com/intsystems/Uncertainty_MachineGen_NIR/blob/main/code), [Slides](https://github.com/intsystems/Uncertainty_MachineGen_NIR/blob/main/slides/21_12_2024_NIR_Report.pdf) | +| Okhotnikov Nikita | Improving algorithmic alignment with autoregressive memory | [Grabovoy A.V.](https://andriygav.github.io) | [Slides](https://github.com/Wayfarer123/ExtraARM-GNN/blob/master/slides/main.pdf), [Code](https://github.com/Wayfarer123/ExtraARM-GNN/tree/master/code), [Paper](https://github.com/Wayfarer123/ExtraARM-GNN/tree/master/paper) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :-------------------- | :----------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Papay Ivan | Ordinal Classification Using Partially Ordered Feature Sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/papayiv/Papay-BS-Thesis/blob/main/code/experiments/mixtures.ipynb) [Paper](https://github.com/papayiv/Papay-BS-Thesis/blob/main/paper/PartialOrders.pdf) [Slides](https://github.com/papayiv/Papay-BS-Thesis/blob/main/slides/PartialOrders_slides.pdf) | +| Meshkov Vladislav | ConvNets Landscape Convergence: Hessian-Based Analysis of Matricized Networks | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/Drago160/Meshkov-paper/blob/master/paper/main.pdf), [Code](https://github.com/Drago160/Meshkov-paper/tree/master), [Slides](https://github.com/Drago160/Meshkov-paper/blob/master/slides/main.pdf) | +| Stepanov Ilia | The use of synthetic data obtained using a generative neural network to improve the quality of detection models | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/ILIAHHne63/Stepanov_Ilia_paper/tree/master/paper), [Code](https://github.com/ILIAHHne63/Stepanov_Ilia_paper/tree/master/code), [Slides](https://github.com/ILIAHHne63/Stepanov_Ilia_paper/tree/master/slides/paper_slides) | +| Nabiev Muhammadsharif | Inductive Bias in Model Selection | Bakhteev O. Y. | [Paper](https://github.com/mikhmed-nabiev/IB-in-model-selection/blob/main/papers/IB_in_model_selection.pdf), [Code](https://github.com/mikhmed-nabiev/IB-in-model-selection/tree/main/src), [Slides](https://github.com/mikhmed-nabiev/IB-in-model-selection/blob/main/papers/Nabiev2024FirstReport.pdf) | +| Zadvornov Egor | Forecasting social trends with high volatility | Malkov A. S. | [Paper](https://github.com/LoveMyWork/Zadvornov_Egor_paper/blob/master/paper/Zadvornov2024VolatilityTimeSeries.pdf), [Code](https://github.com/LoveMyWork/Zadvornov_Egor_paper/tree/master/src), [Slides](https://github.com/LoveMyWork/Zadvornov_Egor_paper/blob/master/slides/Slides_for_paper.pdf) | +| Rebrikov Aleksei | Investigation of Neural Network Sparsification Mechanisms Based on Weight Importance | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/NoblFriend/bachelor-thesis/tree/IDA), [Slides](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/slides/main.pdf) | +| Firsov Sergey | Neural architecture search with target hardware control | [Bakhteev O. Y.](https://bahleg.site/publications) | [Paper](https://github.com/intsystems/Firsov_FBNet/blob/master/paper/Firsov_FBNet_0.pdf), [Code](https://github.com/intsystems/Firsov_FBNet/tree/master/src), [Slides](https://github.com/intsystems/Firsov_FBNet/blob/master/slides/slides.pdf) | +| Khafizov Fanis | Adaptive Compression in Distributed Optimization | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Khafizov-BS-Thesis/tree/master/slides) | +| Eynullayev Altay | Forecasting models in riemannian phase space | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/paper/paper.pdf), [Code](https://github.com/intsystems/Eynullayev-BS-Thesis/tree/master/code), [Slides]() | +| Rubtsov Denis | Сходимость с оценкой вероятностей больших отклонений для задач выпуклой оптимизации и седловых задач в условиях повышенной гладкости | [Gasnikov A.V.] | [Paper](), [Code](https://github.com/intsystems/Rubtsov-BS-thesis/tree/master/code), [Slides](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/slides/Rubtsov_bachelor_diploma_slides.pdf) | +| Kasiuk Vadim | Application of compression operators in distributed optimization problems | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/KasiukVadim/BacDip24_25/blob/main/docs/Kasiuk2024CompressionForDistributedOptimization.pdf), [Code](https://github.com/KasiukVadim/BacDip24_25/blob/main/notebooks/MethodsNotebook.ipynb), [Slides]() | +| Fedor Sobolevsky | Application of Large Language Models for Hierarchical Summarization of Scientific Texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/intsystems/Sobolevsky-BS-Thesis/tree/main/code),[Paper](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/paper/Sobolevsky2024MindMaps.pdf), [Slides](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/slides/Sobolevsky2024Presentation.pdf) | +| Anastasiia Linich | Топологический анализ математических доказательств, генерируемых большими языковыми моделями на формальном языке Lean4 | Barannikov S.A. | [Code](https://github.com/khilling/diploma/tree/main), [Paper](https://github.com/khilling/diploma/blob/main/srw_text.pdf), [Slides](https://github.com/khilling/diploma/blob/main/srw_presentation.pdf) | +| Karpeev Gleb | Порождающие модели для прогнозирования (наборов временных рядов) в метрическом вероятностном пространстве | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/intsystems/2024-Project-152/blob/master/code/gen_score_based_models.ipynb), [Paper](https://github.com/intsystems/2024-Project-152/blob/master/paper/diploma.pdf), [Slides](https://github.com/intsystems/2024-Project-152/blob/master/slides/Karpeev.pdf) | + +### 2024 Spring + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :--------------------------------------------------------------------------------- | :--: | :-------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| [Vasiliy Alekseev](http://www.machinelearning.ru/wiki/index.php?title=User:Alvant) | 4 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper1](https://www.dialog-21.ru/media/4281/alekseevva.pdf), [Paper2](https://aclanthology.org/2020.lrec-1.833), [Paper3](https://www.sciencedirect.com/science/article/pii/S0169023X21000483); [Slides1](http://www.machinelearning.ru/wiki/images/4/49/Iterative_improvement_of_an_additive_regularized_topic_model.pdf), [Slides2](http://www.machinelearning.ru/wiki/images/f/f2/Determination_of_the_Number_of_Topics_Intrinsically_Is_It_Possible_.pdf) | +| Novitskii Vasilii | 3 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](https://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Paper 3](https://proceedings.mlr.press/v162/gasnikov22a.html), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing), [Text](https://disk.yandex.ru/i/vJCKpWGPNBTLTQ) | +| Alexey Grishanov | 2 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper 1](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Paper 2](https://2024.naacl.org/program/accepted_papers/), [Code](https://github.com/milteam/unsupervised-summary-based-segmentation), [Slides]() | +| Panchenko Sviatoslav | 2 | Graph diffusion models for the task of brain signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code), [Slides](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanhenkoIDP2022slides.pdf), [Paper1](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoPaper1Translated.pdf) | +| Pavel Severilov | 2 | Decoding of multimodal signals of brain activity | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper1](https://github.com/severilov/phd-thesis/blob/main/slides/NabievSeverilov2024SignalToAudio.pdf) [Paper2](https://github.com/severilov/phd-thesis/blob/main/slides/noether_lnn_severilov_eng.pdf) [Thesis](https://github.com/severilov/phd-thesis/blob/main/report/phd_thesis.pdf), [Code](https://github.com/severilov/phd-thesis), [Slides Paper1](https://github.com/severilov/phd-thesis/blob/main/slides/NabievSeverilov_EEG_audio2024.pdf) | +| Denis Tikhonov | 2 | Attractor reconstruction for linearized system with miltilinear map | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/Denis-Tihonov/TensorDynamic/tree/main/code), [Slides Paper1](https://github.com/Denis-Tihonov/TensorDynamic/blob/main/slides/Tikhonov2024TensorReconstruction.pdf) | +| Viktor Pankratov | 1 | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/PankratovPHD2024/blob/main/paper/Pankratov_MS_Thesis.pdf),[Code](https://github.com/intsystems/PankratovPHD2024/tree/main/code),[Slides](https://github.com/intsystems/PankratovPHD2024/blob/main/slides/slides_spring2024.pdf) | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :---------------------- | :--------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Klypa Roman | Generative modeling for protein structure and interactions | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/) | [Paper](https://github.com/romanklypa/intsystems_thesis/blob/main/icml2024.pdf), [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/slides_nir2024spring.pdf), [Code](https://github.com/ljk-rk/MolBindDif) | +| Kovaleva Maria | Addition of external information for enhancement of local embeddings for event sequences data models | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://arxiv.org/pdf/2404.02047), [Thesis](https://github.com/MarKovka20/transactions_gen_models/blob/main/thesis.pdf), [Slides](https://github.com/MarKovka20/transactions_gen_models/blob/main/Kovaleva_Maria_predefence_for_MIPT.pdf), [Code](https://github.com/MarKovka20/transactions_gen_models/tree/main) | +| Grigoriy Ksenofontov | Adversarial Schrödinger Bridges | [Roman Isachenko]() | [Code](https://github.com/gregkseno/masters-thesis/blob/master/code/adversarial_ipfp.ipynb), [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/4th/4th%20term.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/paper.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/mipt.pdf) | +| Konstantin Yakovlev | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/paper/HPO.pdf), [Slides](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/slides/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/HyperOpt/tree/main) | +| Tolmachev Alexander | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Paper](https://openreview.net/forum?id=huGECz8dPp), [Paper2](https://arxiv.org/pdf/2403.02187), [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Report.pdf) | +| Polina Barabanshchikova | Tverberg type theorems | [Polyanskii A.A.](http://polyanskii.com/) | [Draft](https://github.com/pollinab/MasterThesis/blob/main/Tverberg_graphs_on_hyperboloid.pdf), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_Tverberg_SVM.pdf), [Code](https://github.com/pollinab/MasterThesis/blob/main/TverbergSVM.ipynb) | +| Alkin Emil | Expressive Power of Recurrent Neural Networks, II | [Ivan Oseledets](https://faculty.skoltech.ru/people/ivanoseledets) | [Draft](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/tensors_strong_hyp_sketch.pdf), [Slides](), [Code](https://github.com/AlkinEmil/MasterThesisPublic) | + +#### Master's Students (1st year) + +| Student | Thesis topic | Advisor | Links | +| :----------------- | :------------------------------------------------------ | :------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Boeva Galina | Label Attention Network for Temporal Sets prediction | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Full Paper](https://github.com/Gaechka777/NIR_2024/blob/main/full_paper.pdf) [Paper](https://github.com/Gaechka777/NIR_2024/blob/main/paper/Boeva2024LabelRelation.pdf), [Slides](https://github.com/Gaechka777/NIR_2024/blob/main/slides/Final_presentation_.pdf), [Code](https://github.com/Gaechka777/NIR_2024/tree/main) | +| Chumachenko Arina | Machine learning methods for functional brain mapping | [Sharaev M. G.](https://faculty.skoltech.ru/people/msharaev) | [Paper](https://github.com/arina-chumachenko/NIR2024/tree/main/paper), [Slides](https://github.com/arina-chumachenko/NIR2024/blob/main/slides/ChumachenkoNIR2024.pdf), [Code](https://github.com/arina-chumachenko/NIR2024/tree/main) | +| Marat Khusainov | Adaptive sampling methods using diffusion models | [Samsonov S.V.]() | [Paper](https://github.com/maratkhusainov/NIR2024-main/blob/master/paper/paper.pdf), [Slides](https://github.com/maratkhusainov/NIR2024-main/blob/master/slides/slides.pdf) , [Code](https://github.com/maratkhusainov/NIR2024-main/tree/master/code) | +| Kornilov Nikita | Optimal Flow Matching | Gasnikov A.V. | [Paper](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/paper/Optimal_Flow_matching_v17_05.pdf), [Slides](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/slides/OFM_NIR_Spring_2024.pdf), [Code](https://github.com/intsystems/Kornilov_2024_NIR/blob/master/notebooks/ofm_alae.ipynb) | +| Kseniia Petrushina | Quantifying image realism via language model reasonings | [Alexander Panchenko](https://msc.skoltech.ru/alexanderpanchenko) | [Paper](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/paper/Quantifying2024Petrushina.pdf), [Slides](https://github.com/intsystems/Petrushina_2024_NIR/blob/master/slides/Quantifying2024Slides.pdf) , [Code](https://github.com/intsystems/Petrushina_2024_NIR/tree/master/code) | +| Parviz Karimov | Representation learning for collections of data | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/IPPK93/Karimov_2024_NIR/blob/master/paper/paper.pdf), [Slides](https://github.com/IPPK93/Karimov_2024_NIR/blob/master/slides/slides.pdf), [Code](https://github.com/IPPK93/Karimov_2024_NIR/tree/master) | +| Dmitry Protasov | Automatic Music Transcription | Ivan Matveev | [Paper](https://github.com/intsystems/2024-Project-165/blob/master/paper/paper_spring_2024.pdf), [Slides](https://github.com/intsystems/2024-Project-165/blob/master/paper/final_talk_18_05.pdf), [Code](https://github.com/intsystems/2024-Project-165/tree/master/code) | +| German Gritsai | Automatic Detection of Machine Generated Texts | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/grgera/Text-detection-dataset/blob/main/nir/poisk_iskusstveno_sgen_frags.pdf), [Paper 2](https://github.com/grgera/Text-detection-dataset/blob/main/nir/Need%20More%20Tokens.pdf), [Slides](https://github.com/grgera/Text-detection-dataset/blob/main/nir/mipt_nir-3.pdf) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :------------------ | :------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Nikita Kiselev | Bayesian Sample Size Estimation | [Grabovoy A. V.](https://andriygav.github.io) | [Thesis](https://github.com/intsystems/Kiselev-BS-Thesis), [Paper 1](https://github.com/kisnikser/Posterior-Distributions-Proximity/blob/main/paper/main.pdf), [Code 1](https://github.com/kisnikser/Posterior-Distributions-Proximity/tree/main/code), [Paper 2](https://github.com/kisnikser/Likelihood-Bootstrapping/blob/main/paper/main.pdf), [Code 2](https://github.com/kisnikser/Likelihood-Bootstrapping/tree/main/code), [Slides](https://www.overleaf.com/read/gvvjjvgqhmkb#211daf) | +| Andrey Veprikov | A Mathematical Model of the Hidden Feedback Loop Effect in Machine Learning Systems | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Paper](https://github.com/intsystems/Veprikov-BS-Thesis/tree/master/paper), [Code](https://gitlab.com/repeated_ml/dynamic-systems-model), [Slides](https://github.com/intsystems/Veprikov-BS-Thesis/tree/master/slides) | +| Ilgam Latypov | Balancing Efficiency and Interpretability: A New Approach to Multi-Objective Optimization with High Computation Costs in Lipschitz Functions | [Dorn Y.V.](https://scholar.google.ru/citations?user=ByIc-l8AAAAJ&hl=ru) | [Paper](https://github.com/intsystems/NIR_LatypovIM/blob/main/docs/Diploma_paper.pdf), [Code](https://github.com/intsystems/NIR_LatypovIM/tree/main/code), [Slides](https://github.com/intsystems/NIR_LatypovIM/blob/main/docs/Diploma_presentation.pdf) | +| Anna Remizova | reducing the dimension of the space of the trainable parameters in the domain adaptation problem | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/slides) | +| Anastasia Voznyuk | Detection of machine-generated fragments based on text style change analysis | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Voznyuk-BS-Thesis/blob/master/paper/SemEval2024_Camera_Ready_Version/Leveraging_Transfer_Learning_for_Detecting_Boundaries_of_Machine-Generated_Texts.pdf), [Code](https://github.com/intsystems/Voznyuk-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Voznyuk-BS-Thesis/tree/master/slides/2024_5_18_NIR_Report.pdf) | +| Dorin Daniil | Spatial-temporal characteristics in the time series decoding | [Grabovoy A. V.](https://andriygav.github.io) | [Paper 1](https://github.com/DorinDaniil/Forecasting-fMRI-Images/blob/main/paper/main.pdf), [Code 1](https://github.com/DorinDaniil/Forecasting-fMRI-Images/blob/main/code/main.ipynb), [Paper 2](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/paper/main.pdf), [Code 2](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/code/main.ipynb), [Slides](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/slides/slides.pdf) | +| Semkin Kirill | Tensor decomposition and forecast for multidimensional time series | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/intsystems/tssa_method/blob/master/doc/Tensor_SSA_Semkin.pdf), [Code](https://github.com/intsystems/tssa_method/tree/master/src), [Slides](https://github.com/intsystems/tssa_method/blob/master/doc/slides/Slides.pdf) | +| Nikitina Maria | Analysis of distribution bias in contrastive learning | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/intsystems/Nikitina-BS-Thesis/blob/master/paper/NikitinaPaper.pdf), [Code](https://github.com/intsystems/Nikitina-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Nikitina-BS-Thesis/tree/master/slides) | +| Babkin Petr | Differential Neural Ensemble Search with Diversity Control | [Bakhteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Oleg_Bakhteev) | [Paper](https://github.com/intsystems/2023-Project-120/blob/master/paper/EdgeNES.pdf), [Code](https://github.com/intsystems/2023-Project-120/tree/master/code), [Slides](https://github.com/intsystems/2023-Project-120/blob/master/slides/slides_1.pdf) | +| Ignashin Igor | Bayesian distillation of transformer-based models | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](), [Code](https://github.com/intsystems/Ignashin-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Ignashin-BS-Thesis/tree/master/slides) | +| Terentyev Alexander | Classification of trajectories of dynamic systems using physically-informed neural networks | [Strijov V.V.](https://scholar.google.ru/citations?user=3TpENmIAAAAJ&hl=en) | [Paper](https://github.com/intsystems/Terentev-BS-Thesis/blob/master/paper/LNN_Classificator.pdf), [Code](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/slides/Slides.pdf) | +| Matvei Kreinin | Methods with preconditioning and weight decaying | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/paper.pdf), [Code](https://github.com/intsystems/Kreinin-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/slides/slides.pdf) | +| Alexander Bogdanov | Application of zero-order stochastic approximation with memoization technique in the Frank-Wolfe algorithm | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/paper/BachelorThesis_paper.pdf), [Code](https://github.com/intsystems/Bogdanov-BS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/slides/BachelorThesis_slides.pdf) | +| Okhotnikov Nikita | Interconnected latent representations for outfit generation task | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/Wayfarer123/BS_Thesis/blob/main/paper/main.pdf), [Code](https://github.com/intsystems/Okhotnikov-BS-Thesis/tree/main/code), [Slides](https://github.com/Wayfarer123/BS_Thesis/blob/main/slides/slides.pdf) | +| Oleinik Mikhail | Knowledge distillation in deep neural networks using model structure alignment methods | [Bakhteev O.Y.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) | [Paper](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Oleinik-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/slides/main.pdf) | + +### 2023 Fall + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :------------------- | :--: | :------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Viktor Pankratov | 1 | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/PankratovPHD2023/blob/main/paper/Pankratov_MS_Thesis.pdf),[Code](https://github.com/intsystems/PankratovPHD2023/tree/main/code),[Slides](https://github.com/intsystems/PankratovPHD2023/blob/main/slides/PankratovAut2023Slides.pdf) | +| Pavel Severilov | 2 | Decoding of multimodal signals of brain activity | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/severilov/phd-thesis/blob/main/report/phd_thesis.pdf), [Code](https://github.com/severilov/phd-thesis), [Slides](https://github.com/severilov/phd-thesis/tree/main/slides) | +| Alexey Grishanov | 2 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper 1](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Paper 2 - under review](), [Code](https://github.com/intsystems/GrishanovPHD2022/tree/main/code), [Slides]() | +| Novitskii Vasilii | 3 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](https://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Paper 3](https://proceedings.mlr.press/v162/gasnikov22a.html), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing) | +| Vasiliy Alekseev | 4 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Conf1](https://www.youtube.com/live/EdhnmkhkUiQ?feature=shared&t=6980) ([Slides1](http://www.machinelearning.ru/wiki/images/d/d4/Determination_of_the_Number_of_Topics_Intrinsically_Is_It_Possible.pdf)), [Slides2](http://www.machinelearning.ru/wiki/images/0/05/TopicBank._Collection_of_Coherent_Topics_Using_Multiple_Model_Training_with_Their_Further_Use_for_Topic_Model_Validation.pdf) | +| Tikhonov Denis | 2 | Dimensionality reduction of tensor phase spaces in nonlinear dynamical system reconstruction | [Strijov V.V.](http://www.ccas.ru/strijov/) | ([Slides](https://github.com/Denis-Tihonov/TensorDynamic/blob/main/slides/Tikhonov2024Tensors.pdf)), [Code](https://github.com/Denis-Tihonov/TensorDynamic/tree/main/code) | +| Panchenko Sviatoslav | 2 | Graph Diffusion models for human brain activity decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoPaper1Translated.pdf), [Slides](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoPaper2Slides.pdf), [Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code) | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :---------------------- | :----------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Rustem Islamov | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Paper](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Paper/Islamov2023MasterThesis.pdf), [Code](https://github.com/intsystems/Islamov-MS-Thesis/tree/main/Code), [Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf) | +| Kovaleva Maria | Addition of global information for enhancement of local embeddings for transactional data models | [Zaytsev A.A](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/MarKovka20/masters_nir/blob/main/thesis.pdf), [Slides](https://github.com/MarKovka20/masters_nir/blob/main/nir_preso.pdf) | +| Tolmachev Alexander | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Paper](https://openreview.net/forum?id=huGECz8dPp), [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Report.pdf) | +| Klypa Roman | Generative modeling for protein structure and interactions | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/) | [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/slides_nir2023fall.pdf), [Code](https://gricad-gitlab.univ-grenoble-alpes.fr/GruLab/multi-partner-diff) | +| Polina Barabanshchikova | Tverberg type theorems | [Polyanskii A.A.](http://polyanskii.com/) | [Paper](https://www.sciencedirect.com/science/article/pii/S0012365X23003801?via%3Dihub), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_Tverberg.pdf) | +| Konstantin Yakovlev | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/paper/HPO.pdf), [Slides](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/slides/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/HyperOpt/tree/main) | +| Grigoriy Ksenofontov | Adversarial Schrödinger Bridges | [Roman Isachenko]() | [Code](https://github.com/gregkseno/master-thesis), [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/3d/3d%20term.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/main.tex) | +| Alkin Emil | Expressive Power of Recurrent Neural Networks, II | [Ivan Oseledets](https://faculty.skoltech.ru/people/ivanoseledets) | [Draft](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/tensors_strong_hyp_sketch.pdf), [Slides](), [Code]() | + +#### Master's Students (1st year) + +| Student | Topic | Advisor | Links | +| :------------------ | :--------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------- | +| Yakovlev Konstantin | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/e0695bf94256170ceb6e2860815b1f45bea950eb/paper/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/Concord-NAS/tree/rnn), [Slides](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/rnn/slides/main.pdf) | +| Galina Boeva | Identifying the relationship between labels using an attention-based algorithm for the Next Basket Recommendation task | [Zaytsev A.A](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/Gaechka777/Temporal_sets/tree/main/paper) [Code](https://github.com/Gaechka777/Temporal_sets/tree/main) [Slides](https://github.com/Gaechka777/Temporal_sets/tree/main/slides) | +| Bair Mikhailov | Undersampled MRI Reconstruction | [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Slides](https://github.com/intsystems/MRI_Reconstruction/blob/master/slides/slides.pdf) | +| Pavel Bartenev | MRI data augmentation via conditional generative 3D inpainting | [Maxim Sharaev](https://faculty.skoltech.ru/people/msharaev) | [Slides](https://github.com/intsystems/MRI-Inpainting/tree/master/slides) [Code](https://github.com/intsystems/MRI-Inpainting/tree/master/code) | +| Kseniia Petrushina | Detection of hallucinations of language models | [Alexander Panchenko](https://msc.skoltech.ru/alexanderpanchenko) | [Slides](https://github.com/intsystems/Petrushina_2024_NIR/blob/сonsistency/slides/Consistency2023Slides.pdf) [Code](https://github.com/intsystems/Petrushina_2024_NIR/tree/сonsistency/code) | +| Arina Chumachenko | Machine learning methods for functional brain mapping | [Maxim Sharaev](https://msc.skoltech.ru/maxim-sharaev) | [Slides](https://github.com/intsystems/Chumachenko_2023_NIR/blob/master/slides/Chumachenko_NIR2023.pdf) | [Code](https://github.com/intsystems/Chumachenko_2023_NIR/tree/master/code/main.ipynb) | +| Nikita Kornilov | Intermediate Gradients Methods with Relative Inexactness | Alexandr Gasnikov | [Slides](https://github.com/intsystems/Kornilov_2023_NIR/blob/master/slides/InterRel_pres_rus.pdf) [Code](https://github.com/intsystems/Kornilov_2023_NIR/blob/master/code/Numerical_exp_ISTM.ipynb) [Paper](https://github.com/intsystems/Kornilov_2023_NIR/blob/master/paper/2023_JOTA_Intermediate_Methods_with_Relative_Inexactness.pdf) | +| Dmitry Protasov | Automatic Music Transcription | Ivan Matveev | [Slides](https://github.com/Vosatorp/MusicNIR/blob/main/docs/MusicNIR_Slides.pdf) [Code](https://github.com/Vosatorp/MusicNIR/blob/main/code) [Draft](https://github.com/Vosatorp/MusicNIR/blob/main/docs/MusicNIR_Paper.pdf) | +| Parviz Karimov | Representation learning for data point groups | [Roman Isachenko](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Slides](https://github.com/intsystems/Karimov_2023_NIR/tree/master/slides) [Draft](https://github.com/intsystems/Karimov_2023_NIR/tree/master/paper) | +| Eduard Vladimirov | Adversarial attacks on neural networks for time series | [Zaytsev A.A](https://faculty.skoltech.ru/people/alexeizaitsev) | [Slides](https://github.com/intsystems/Vladimirov_2023_NIR/blob/master/slides/eavladimirov_2023_nir.pdf) [Code](https://github.com/intsystems/Vladimirov_2023_NIR/tree/master/code) [Draft](https://github.com/intsystems/Vladimirov_2023_NIR/blob/master/paper/Vladimirov_2023_paper.pdf) | +| Zharov Georgiy | Search for an effective architecture for solving the problem of obtaining multimodal embeddings for three or more modalities | | [Slides](https://github.com/Egor-s-gor/Zharov_2023_NIR/tree/main/slides) [Code](https://github.com/Egor-s-gor/Zharov_2023_NIR/tree/main/code) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :------------------ | :--------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Antyshev Tikhon | Gradient Sliding for Saddle Point problems with one composite | Gasnikov A. V. | [Code](https://github.com/intsystems/Antyshev-BS-Thesis) [Paper](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/paper/SaddleSlidingArticle.pdf) [Slides](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/slides/slides.pdf) | +| Kiselev Nikita | Bayesian Sample Size Estimation | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Kiselev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/slides/main.pdf) | +| Kreinin Matvei | On methods with preconditioning and weight decaying | [Beznosikov A. N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/kreininmv/NIR/blob/master/paper.pdf), [Code](https://github.com/kreininmv/NIR/tree/master/code), [Slides](https://github.com/kreininmv/NIR/blob/master/slides.pdf) | +| Ilgam Latypov | Research On multicriteria optimization using Shapley Value | [Dorn Y.V.](https://scholar.google.ru/citations?hl=ru&user=ByIc-l8AAAAJ&view_op=list_works&sortby=pubdate) | [Paper](https://github.com/intsystems/NIR_LatypovIM/tree/main/docs/НИР_english.pdf), [Code](https://github.com/intsystems/NIR_LatypovIM), [Slides](https://github.com/intsystems/NIR_LatypovIM/tree/main/docs/НИР_презентация.pdf) | +| Anastasiia Vozniuk | Detection of Machine-Generated Fragments in Text | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/2023-Project-126/blob/master/paper/DetectionOfFragments2023_14_12.pdf), [Code](https://github.com/intsystems/2023-Project-126/tree/master/code), [Slides](https://github.com/intsystems/2023-Project-126/blob/master/slides/2023_12_16_SlidesReport.pdf) | +| Terentyev Alexander | Classification of trajectories of dynamic systems with physics-informed neural networks | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/paper/paper.pdf), [Code](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/paper/LNN_Classificator_Slides.pdf) | +| Veprikov Andrey | A mathematical model of the hidden feedback loop effects in machine learning systems | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Paper](https://www.overleaf.com/read/whbcvrmnhgpj#914b2d), [Code](https://gitlab.com/repeated_ml/2023-project-119), [Slides](https://www.overleaf.com/read/nrhdjnjmxfqd#517273) | +| Ignashin Igor | Bayesian distilation of transformer-based models | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/paper/Paper_Bayesian_distilation_Ignashin_BS_Thesis.pdf), [Code](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/code/RNN_attention.ipynb), [Slides](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/slides/Presentation_Bayesian_distilation_Ignashin_BS_Thesis.pdf) | +| Remizova Anna | Altering latent representation in the audio style transfer task | [Grabovoy A.V.](https://andriygav.github.io) | [Paper](https://github.com/AnnaRemi/BachelorThesis/tree/master/paper/Thesis_paper.pdf), [Code](https://github.com/AnnaRemi/BachelorThesis/blob/master/code/Baseline_Style_Transfer.ipynb), [Slides](https://github.com/AnnaRemi/BachelorThesis/blob/master/slides/presentation_autumn_23.pdf), [Paper handwritten draft](https://github.com/AnnaRemi/BachelorThesis/blob/master/literature/notes/thesis.pdf) | +| Babkin Petr | Differential neural ensemble search with diversity control | Bakhteev O.Y. | [Paper](https://github.com/intsystems/2023-Project-120/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/2023-Project-120/tree/master/code), [Slides](https://github.com/intsystems/2023-Project-120/blob/master/slides/slides_for_m1p.pdf) | +| Nikitina Maria | Analysis of distribution bias in contrastive learning | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/NikitinaMaria/Contrastive_learning/blob/main/Paper/NikitinaPaper.pdf), [Code](https://github.com/NikitinaMaria/Contrastive_learning/tree/main/Code), [Slides](https://github.com/NikitinaMaria/Contrastive_learning/blob/main/Paper/Presentation/NikitinaSlides.pdf) | +| Oleinik Mikhail | Knowledge distillation in deep neural networks using model structure alignment methods | [Bakhteev O.Y.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) | [Paper](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/paper/main.pdf), [Code](https://github.com/intsystems/Oleinik-BS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/slides/main.pdf) | +| Semkin Kirill | Tensor-SSA method in application to time series decomposition | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/sem-k32/scientific_work_Semkin/blob/master/doc/Tensor_SSA_Semkin.pdf), [Code](https://github.com/sem-k32/scientific_work_Semkin/blob/master/main_experiment.ipynb), [Slides](https://github.com/sem-k32/scientific_work_Semkin/blob/master/doc/slides/Slides.pdf) | +| Bogdanov Alexander | New Aspects of Black Box Conditional Gradient: Variance Reduction and One Point Feedback | [Beznosikov A. N.](https://anbeznosikov.github.io/) | [Paper](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/paper/BachelorThesis_paper.pdf), [Code](https://github.com/intsystems/Bogdanov-BS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/slides/BachelorThesis_slides.pdf) | +| Dorin Daniil | Spatial-temporal characteristics in the time series decoding | [Grabovoy A. V.](https://andriygav.github.io) | [Paper](https://github.com/Daniilmipt007/project_VKR/blob/master/paper/main.pdf), [Code](https://github.com/Daniilmipt007/project_VKR/blob/master/code), [Slides](https://github.com/Daniilmipt007/project_VKR/blob/master/slides/pres_NIR.pdf) | +| Okhotnikov Nikita | Interconnected latent representations for outfit generation task | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Paper](https://github.com/Wayfarer123/BS_Thesis/blob/main/paper/main.pdf), [Code](https://github.com/intsystems/Okhotnikov-BS-Thesis/tree/main/code), [Slides](https://github.com/Wayfarer123/BS_Thesis/blob/main/slides/slides.pdf) | + +### 2023 Spring + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :------------------- | :--: | :-------------------------------------------------------------------------- | :------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Pavel Severilov | 1 | Decoding of multimodal signals of brain activity | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/severilov/phd-thesis), [Slides](https://github.com/severilov/phd-thesis/tree/main/slides) | +| Grishanov Alexey | 1 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Code](https://github.com/intsystems/GrishanovPHD2022/tree/main/code), [Slides]() | +| Panchenko Sviatoslav | 1 | Graph Diffusion Models for the Task of Signal Decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper (Translated, draft)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanchenkoArticle2023Translated.pdf), [Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code), [Slides (IDP conf.)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanhenkoIDPslides.pdf) | +| Vasilii Novitskii | 2 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing) | +| Alina Samokhina | 2 | Continous-in-time representations of signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code old](https://github.com/Alina-Samokhina/continuous_time_paper), [Paper draft](https://www.overleaf.com/read/bvrwfjgxnrjr), [Slides](https://www.overleaf.com/read/mhwjngzpfmps) | +| Vasiliy Alekseev | 3 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper (draft)](https://github.com/intsystems/2023-Project-131/blob/master/paper/Gorbulev2023TopicModels.pdf), [Slides](https://github.com/intsystems/2023-Project-131/blob/master/slides/Gorbulev2023TopicModelsPresentation.pdf) | +| Aleksei Goncharov | 4 | Space-time series alignment models | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Papers](https://scholar.google.com/citations?user=umbRPRkAAAAJ&hl=en), [Slides](https://github.com/lexix/Goncharov_PhDThesis/blob/main/Goncharov%20-%20Dissertation.pdf), [Thesis](https://www.overleaf.com/project/62b8bc7c4162ad51f49f5087) | +| Petr Ostroukhov | 4 | Tensor Methods for Convex Functions Minimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper](https://www.overleaf.com/read/ghshtbymmwym), [Slides](https://disk.yandex.ru/i/9J6zoJHwsMRwqg) | +| Denis Kuznetsov | 4 | Neural network models of dialogue on general topics | [Burtsev M.S.](https://scholar.google.ru/citations?hl=ru&user=t_PLQakAAAAJ) | [Paper with Code](https://paperswithcode.com/paper/imad-image-augmented-multi-modal-dialogue) | +| Radoslav Neychev | 4 | Informative prior in privileged learning | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Old paper](http://strijov.com/papers/Shibaev2022Symbolic.pdf), [Paper 1](https://drive.google.com/file/d/1sywZxS5bTXWPzzgUnqzgAH3QZow4BUAi/view?usp=sharing), New paper 2 (in blind review for now) | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :------------------ | :--------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Rustem Islamov | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Paper](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Paper/Islamov2023MasterThesis.pdf), [Code](https://github.com/intsystems/Islamov-MS-Thesis/tree/main/Code), [Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf) | +| Filatov Andrei | Text interfaces for event sequences | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/paper/FilatovMIPTThesis.pdf), [Slides](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/slides/FilatovMScThesisPresentation.pdf) | +| Shokorov Viacheslav | Bootstrapping of neural network ensembles | Vetrov D.P. | [Text (draft)](https://docs.google.com/document/d/1RcN3YLLUrVhFr6rNHz43iKaO3CtJeRv-D9KY7nvhWv4/edit?usp=sharing) [Slides](https://github.com/vshokorov/margin_based_ensembles_boosting/blob/main/reports/Slides_spring2023.pdf), [Code](https://github.com/vshokorov/margin_based_ensembles_boosting) | +| Safiullin Robert | Multimodel representation of dynamic systems | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Safiullin-MS-Thesis/blob/master/paper/master_diploma.pdf) [Slides](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/slides), [Code](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/code) | +| Bishuk Anton | Controlled Graph Generation | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Paper](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/paper/paper.pdf), [Code](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/slides/slides.pdf) | +| Pankratov Viktor | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/paper), [Code](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/slides) | +| Grebenkova Olga | Automatic detection of focal cortical dysplasia for sparse data representation | [Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) | [Draft](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/Thesis_draft.pdf), [Code](https://github.com/intsystems/Grebenkova-MS-Thesis/tree/main), [Slides](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/MSc_Thesis_PreDefence_Grebenkova.pdf) [Paper](https://www.scitepress.org/Link.aspx?doi=10.5220/0011626900003393) | +| Nadezhda Alsahanova | Selection of tensor representations for multiview forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Draft](https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Doc/Thesis_draft.pdf), [Code](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Code/Final%20code), [Slides](https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Slides/Nadezhda_Alsahanova_SLIDES.pdf) | + +#### Master's Students (1st year) + +| Student | Topic | Advisor | Links | +| :---------------------- | :------------------------------------------------------------------- | :-------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Yakovlev Konstantin | Concordant Neural Architecture Search on Multidomain Data | Bakhteev O. Y. | [Paper](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/e0695bf94256170ceb6e2860815b1f45bea950eb/paper/main.pdf), [Code](https://github.com/Konstantin-Iakovlev/Concord-NAS/tree/rnn), [Slides](https://github.com/Konstantin-Iakovlev/Concord-NAS/blob/rnn/slides/main.pdf) | +| Kovaleva Maria | Neural architecture search with early stopping | [Alexey Zaytsev](https://faculty.skoltech.ru/people/alexeizaitsev) | [Code](https://github.com/MarKovka20/Project_reseach/tree/main), [Slides](https://github.com/MarKovka20/Project_reseach/blob/main/presentation.pdf), [Draft](https://docs.google.com/document/d/1A0nhXXczofwsRUDMEmy6MImaiPf9JAJ5CazqGcetn5Q/edit?usp=sharing) | +| Grigoriy Ksenofontov | Analysis of generative modeling methods based on Schrödinger bridges | [Roman Isachenko]() | [Code](https://github.com/gregkseno/master-thesis), [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/2nd/2nd%20term.pdf), [Draft](https://github.com/gregkseno/master-thesis/blob/master/paper/main.tex) | +| Polina Barabanshchikova | Helly type problems for d-intervals | [Polyanskii A.A.](https://mipt.ru/education/chairs/dm/staff/polyanskii.php) | [Paper](https://arxiv.org/abs/2303.10706), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Helly%20type%20problems%20for%20d-intervals.pdf) | +| Tolmachev Alexander | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Paper](https://arxiv.org/abs/2305.08013), [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Report.pdf) | +| Alkin Emil | Expessive Power of Recurrent Neural Networks | [Oseledets I. V.](https://faculty.skoltech.ru/people/ivanoseledets) | [Slides](https://www.overleaf.com/read/bxvwpmzvnzvp), [Code](https://colab.research.google.com/drive/1mTdzgFeBJbxkDu5zR4Lw5snZ-IGUNL50?usp=sharing) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :--------------------- | :----------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Antyshev Tikhon | Gradient Sliding for Saddle Point problems with one composite | Gasnikov A. V. | [Code](https://github.com/intsystems/Antyshev-BS-Thesis) [Paper](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/paper/SaddleSlidingArticle.pdf) [Slides](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/slides/slides.pdf) | +| Kornilov Nikita | Gradient Free Methods for Non-Smooth Convex Stochastic Optimization with Heavy Tails on Convex Compact | Gasnikov A. V. | [Code](https://github.com/intsystems/Kornilov-BS-Thesis/tree/main) [Paper](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/paper/gradient_free_non_smooth_heavy_tails.pdf) [Slides](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/slides/InfZero_Grad_Pres.pdf) | +| Lukyanenko Ivan | Detection of manipulations and its targets in news texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/intsystems/Lukyanenko-BS-Thesis), [Text](https://www.overleaf.com/read/zbqndyzfydpy), [Slides](https://www.overleaf.com/read/rkdykqwnvbzj) | +| Zharov Georgiy | Classification of manipulative fragments in news texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/models), [Slides](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/slides) | +| Vladimirov Eduard | Choosing a state space model in a neural decoding problem | [Strijov V.V.](<[http://www.machinelearning.ru/wiki/index.php?title=User:Vokov](http://www.ccas.ru/strijov/)>) | [Code1](https://github.com/Edyarich/annotated-s4), [Code2](https://github.com/Edyarich/ECGNet), [Slides](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/slides/VladimirovTSModels.pdf) | +| Molozhavenko Alexander | Solution of a block multidimensional eigenvalues search problem | Gasnikov A.V. | [Slides](https://www.overleaf.com/read/gxtnzbdhzhcj), [Code](https://github.com/intsystems/Molozhavenko-BS-Thesis) | + +### 2022 Fall + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :------------------- | :--: | :-------------------------------------------------------------------------- | :------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Vasiliy Alekseev | 3 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://link.springer.com/article/10.1134/S106456242202003X), [Paper (conf.)](https://link.springer.com/chapter/10.1007/978-3-031-19032-2_12) | +| Grishanov Alexey | 1 | Applying Reinforcement Learning for Recommendation Platform Personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://dl.acm.org/doi/pdf/10.1145/3523227.3551485), [Code](https://github.com/intsystems/GrishanovPHD2022/tree/main/code), [Slides (Sber AI Lab seminar)](https://github.com/intsystems/GrishanovPHD2022/blob/main/paper/sber_ai_lab_seminar.pdf) | +| Panchenko Sviatoslav | 1 | Graph Diffusion Models for the Task of Signal Decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper (Article, draft)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/Panchenko2022ArticleDraft.pdf), [Code](https://github.com/intsystems/PanchenkoPhD2022/tree/main/code), [Slides (IDP conf.)](https://github.com/intsystems/PanchenkoPhD2022/blob/main/paper/PanhenkoIDPslides.pdf) | +| Denis | 1 | Dimension reduction of tensor phase spaces in dynamical system simulation | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Denis-Tihonov/MsThesis/blob/main/Paper/2022Classification_rus.pdf), Code, [Slides](https://github.com/Denis-Tihonov/MsThesis/blob/main/Slides/Tikhonov2022ClassificationPresentation.pdf) | +| Alina Samokhina | 2 | Continous-in-time representations of signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code old](https://github.com/Alina-Samokhina/continuous_time_paper), [Paper published](http://www.ipiran.ru/journal_system/article/08696527220304.html), [Paper draft](https://www.overleaf.com/read/fcwdwfkhthnv), [Slides](https://www.overleaf.com/read/mhwjngzpfmps) | +| Vasilii Novitskii | 2 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing) | +| Polina Potapova | 3 | Topic modeling for multilingual topic search | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://www.overleaf.com/7641677752mmzmcfghzydj), [Code](https://github.com/machine-intelligence-laboratory/text_categorization) | +| | | | | | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :------------------ | :--------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Andrei Filatov | Infinite transformers | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Filatov-MS-Thesis/tree/master/paper), [Code](https://github.com/intsystems/Filatov-MS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Filatov-MS-Thesis/tree/master/slides) | +| Rustem Islamov | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Paper](https://arxiv.org/abs/2206.03588), [Code](https://github.com/intsystems/Islamov-MS-Thesis/tree/main/Code), [Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf) | +| Bishuk Anton | Controlled Graph Generation | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Paper](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/paper), [Code](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Bishuk-MS-Thesis/tree/main/slides) | +| Grebenkova Olga | Automated detection of focal cortical dysplasia | [Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) | [Slides](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/Slides_22.pdf) [Acceptance letter](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/AcceptanceLetter.pdf) | +| Safiullin Robert | Multimodel representation of dynamic systems | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://www.mdpi.com/2227-9040/10/12/520), [Code](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/code), [Slides](https://github.com/intsystems/Safiullin-MS-Thesis/tree/master/slides) | +| Shokorov Viacheslav | Deep ensembles bootstrapping | Vetrov D.P. | [Notes](https://github.com/vshokorov/margin_based_ensembles_boosting/issues/5), [Code](https://github.com/vshokorov/margin_based_ensembles_boosting) | +| Pankratov Viktor | Probabilistic topic modeling | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/paper), [Code](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/code), [Slides](https://github.com/intsystems/Pankratov-MS-Thesis/tree/main/slides) | +| Alsahanova Nadezhda | Selection of tensor representations for multiview forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Doc), [Code](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Code), [Slides](https://github.com/NadezhdaAlsahanova/MSThesis/tree/main/Slides) | + +#### Master's Students (1st year) + +| Student | Topic | Advisor | Links | +| :---------------------- | :-------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Maria Kovaleva | Research of efficient transformers | [Alexey Zaytsev](https://faculty.skoltech.ru/people/alexeizaitsev) | [Paper](https://github.com/MarKovka20/Models-of-sequential-data-project/blob/main/literature_review.pdf), [Code](https://github.com/MarKovka20/Models-of-sequential-data-project), [Slides](https://github.com/MarKovka20/Models-of-sequential-data-project/blob/main/slides.pdf) | +| Roman Klypa | Combination of geometrical learning and language models for bioinformatics | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/) | [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/report.pdf) | +| Polina Barabanshchikova | Helly type problems for d-intervals | [Polyanskii A.A.](https://mipt.ru/education/chairs/dm/staff/polyanskii.php) | [Paper](https://github.com/pollinab/MasterThesis/blob/main/Maximum_spanning_tree.pdf), [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_spanning_tree.pdf) | +| Grigoriy Ksenofontov | Creating a personalized avatar of a person for a virtual fitting of clothes | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov), Yanina A.O. | [Slides](https://github.com/gregkseno/master-thesis/blob/master/slides/1st/1st%20term.pdf) | +| Yakovlev Konstantin | Concordant Neural Architecture Search on multi-domain data | [Bakhteev O.Y.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) | [Slides](https://github.com/Konstantin-Iakovlev/Slides/raw/main/IOI/main.pdf) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :--------------------- | :------------------------------------------------------------------------ | :--------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Eduard Vladimirov | Ways to account for data noise in a Neural ODE model | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/intsystems/Vladimirov-BS-Thesis/raw/master/paper/VladimirovNODEandNoise.pdf), [Code](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/code/main.ipynb), [Slides](https://github.com/intsystems/Vladimirov-BS-Thesis/raw/master/slides/VladimirovNODEandNoiseSlides.pdf) | +| Antyshev Tikhon | Zero-order Mirror Descent for Saddle Point Problems | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru) | [Paper](https://github.com/intsystems/Antyshev-Zero-order-methods-for-SP/tree/master/paper), [Code](https://github.com/intsystems/Antyshev-Zero-order-methods-for-SP), [Slides](https://github.com/intsystems/Antyshev-Zero-order-methods-for-SP/tree/master/slides) | +| Ivan Lukyanenko | Joint NER and RE in manipulation news | Vorontsov K.V. | [Code](https://github.com/AlexeyVatolin/manipulation) [Slides](https://ru.overleaf.com/read/tzjhtywnzvvr) | +| Kornilov Nikita | Gradient Free Optimization with Infinite Variance | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Paper](https://github.com/Jhomanik/KornilovBSThesis/blob/main/paper/GradFree_with_inf__noise.pdf), [Slides](https://github.com/Jhomanik/KornilovBSThesis/blob/main/slides/InfZero_Grad_Pres.pdf) | +| Georgiy Zharov | Search for manipulations and their relations with named entities in texts | Vorontsov K.V. | [Slides](https://drive.google.com/file/d/1oYjCU8GJPjGBfe2d_tHbeBHT1WyB8R5i/view?usp=share_link) | +| Molozhavenko Alexander | Solution of a block multidimensional eigenvalues search problem | Gasnikov A.V. | [Slides](https://www.overleaf.com/read/gxtnzbdhzhcj), [Code](https://github.com/SuperCrabLover/BachelorDiploma) | + +### 2022 Spring + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :--------------- | :--: | :------------------------------------------------------------------------------------------ | :--------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Andrey Grabovoy | 1 | Bayesian Distilation | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/andriygav/PhDThesis), [Thesis](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/35-grabovoy/ds05-35-grabovoy_main.pdf?90) | +| Alina Samokhina | 1 | Continous-time representation for signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/Intelligent-Systems-Phystech/Samokhina-PhD-Thesis), [Paper](https://www.overleaf.com/read/dmtgkgpnnjkg), [Slides](https://www.overleaf.com/read/yjcdsfkscykt) | +| Nikitin Filipp | 2 | Generation and selection of graph neural network models in the problem of organic chemistry | [Strijov V. V.](http://www.machinelearning.ru/wiki/index.php?title=User:Strijov) | [Code](https://github.com/FilippNikitin/Space-of-graphs-of-chemical-reactions) | +| Polina Potapova | 2 | Topic modeling for multilingual topic search | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://www.overleaf.com/9773112327qphbychmbmjp), [Code](https://github.com/machine-intelligence-laboratory/text_categorization) | +| Vasiliy Alekseev | 2 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper (not visible)](https://openreview.net/forum?id=rKZ8XbpS8ec), [Code (private)](https://github.com/machine-intelligence-laboratory/BasisConvs) | +| Ostroukhov Petr | 3 | Tensor methods for convex optimization | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru&oi=ao) | [Paper 1](http://crm.ics.org.ru/journal/article/3189/), [Paper 2](http://crm.ics.org.ru/journal/article/3190/) | +| Kamil Safin | 3 | Combined methods for text plagiarism detection | Chehovich Y.V. | [Paper](https://ispranproceedings.elpub.ru/jour/article/view/1501/1320) | +| Denis Kuznetsov | 3 | Neural network models of dialogue on general topics | [Burtsev M.S.](https://scholar.google.ru/citations?hl=ru&user=t_PLQakAAAAJ) | [Paper_1](https://drive.google.com/file/d/17PLgv8CTQvC0BkJq53Ct1t509lwVepUV/view?usp=sharing), [Paper_2](https://drive.google.com/file/d/1Gg1NUpwNLz42O0Zqp9JyPBSjI0ApzVYg/view?usp=sharing) | +| Ilia Zharikov | 4 | Neural network methods for document image recognition | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/MIL-Compression-Team/QuantInit/blob/dev/docs/Paper.pdf), [Code](https://github.com/MIL-Compression-Team/QuantInit), [Slides](https://github.com/MIL-Compression-Team/QuantInit/blob/dev/docs/Slides.pdf) | +| Alex Goncharov | 3 | Space-time series alignment models | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Papers](https://scholar.google.com/citations?user=umbRPRkAAAAJ&hl=en), [Slides](https://github.com/lexix/Goncharov_PhDThesis/blob/main/Goncharov%20-%20Dissertation.pdf) | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :------------------- | :----------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Petr Mokrov | Wasserstein gradient flows: modeling and applications | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ&hl=en) | [Paper](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/blob/master/paper/Mokrov2022_master_thesis.pdf), [Code](https://github.com/PetrMokrov/Large-Scale-Wasserstein-Gradient-Flows), [Slides](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/blob/master/slides/Mokrov2022_ms_defense_presentation.pdf) | +| Denis Tikhonov | Quasiperiodic time signals classification with spherical harmonics | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Denis-Tihonov/MsThesis/blob/main/Paper/Tikhonov2022Classification_rus.pdf), Code, [Slides](https://github.com/Denis-Tihonov/MsThesis/blob/main/Slides/Tikhonov2022ClassificationPresentation.pdf) | +| Natalia Varenik | Building a connectivity map of functional groups in the problem of decoding brain signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/paper/Varenik2022master_thesis.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/tree/master/code), [Slides](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/slides/master_thesis_presentation.pdf) | +| Alexey Grigorev | Regularization of neural layer via construction of frame in parameter space | [Gneushev A.N.](https://scholar.google.com/citations?hl=en&user=sjlY2q8AAAAJ) | [Slides](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/slides.pdf), [Code](https://github.com/formica-rufa/WO), [Paper](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/thesis.pdf) | +| Kolesov Aleksandr | Adverasrial method for Transfer Learning based on Optimal Transport | [Bakhteev O.Y](https://scholar.google.ru/citations?hl=ru&user=7eWNuFkAAAAJ&view_op=list_works&sortby=pubdate) | [Paper](https://github.com/Kolessov/Optimal-Transfer-Learning/blob/main/Diplome_pre.pdf), [Code](https://github.com/Kolessov/Optimal-Transfer-Learning), [Slides](https://github.com/Kolessov/Optimal-Transfer-Learning/blob/main/Presentation.pdf) | +| Severilov Pavel | Choosing the optimal model in the problem of modeling dynamics of a physical system by neural networks | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/severilov/master-thesis/blob/main/doc/Severilov2022MasterThesis_rus.pdf) [Slides](https://github.com/severilov/master-thesis/blob/main/pres/Severilov2022MasterThesisPres.pdf) [Code](https://github.com/severilov/master-thesis/tree/main/code) [Paper2](http://crm.ics.org.ru/uploads/crmissues/crm_2022_02/2022_02_10.pdf) | +| Panchenko Sviatoslav | Bilinearity of geometric product for the task of signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/paper/Panchenko2022MasterThesis.pdf), [Slides](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/slides/Panchenko2022MasterPresentation.pdf) [Code](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/tree/main/code) | +| Grishanov Alexey | Application of Reinforcement Learning for recommendation system personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/shashist/master_thesis/blob/main/Grishanov2022Thesis.pdf), [Slides](https://drive.google.com/file/d/1AKAz5hTMEd0ig9ob_WvJwluz0O5Zk0A2/view?usp=sharing), [Сode](https://github.com/AILab-MLTools/RePlay) | + +#### Master's Students (1st year) + +| Student | Topic | Advisor | Links | +| :------------------ | :---------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Rustem Islamov | Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning | [Richtarik P.](https://richtarik.org/), [Strijov V.V.](http://strijov.com/papers_en.html) | [Paper](https://proceedings.mlr.press/v151/qian22a.html), [Code](https://github.com/Intelligent-Systems-Phystech/Islamov-MS-Thesis/tree/master/Code), [Slides](https://github.com/Intelligent-Systems-Phystech/Islamov-MS-Thesis/blob/master/Presentation/Islamov-MS-Presentation-2022.pdf) | +| Bishuk Anton | Controlled graph generation using the variational autoencoder model | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Report](https://github.com/Intelligent-Systems-Phystech/Bishuk-MS-Thesis-public/blob/master/abstract.pdf) | +| Grebenkova Olga | Automated detection of focal cortical dysplasia | [Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) | [Report](https://github.com/Intelligent-Systems-Phystech/Grebenkova-MS-Thesis-public/blob/master/Report_22.pdf) | +| Filatov Andrei | Novel view synthesis | Lempitsky Victor | [Slides](https://github.com/Intelligent-Systems-Phystech/Filatov-MS-Thesis/blob/master/FilatovAndreiS10.pdf) [Code](https://github.com/Intelligent-Systems-Phystech/Filatov-MS-Thesis) | +| Safiullin Robert | Multimodel representation of dynamic systems | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Intelligent-Systems-Phystech/Safiullin-MS-Thesis/blob/master/Paper/readme.md), [Code](https://github.com/Intelligent-Systems-Phystech/Safiullin-MS-Thesis/blob/master/code/code.ipynb), [Slides](https://github.com/Intelligent-Systems-Phystech/Safiullin-MS-Thesis/blob/master/slides/SafiullinMS_slides_2.pdf) | +| Pankratov Viktor | Topic balancing of topic models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Code](https://github.com/Intelligent-Systems-Phystech/Pankratov-MS-Thesis/blob/main/%D0%9D%D0%98%D0%A0_%D0%92%D0%B5%D1%81%D0%BD%D0%B02022_%D0%BA%D0%BE%D0%B4.ipynb), [Slides](https://github.com/Intelligent-Systems-Phystech/Pankratov-MS-Thesis/blob/main/slides_spring_2022.pdf) | +| Shokorov Viacheslav | Bootstrapping of neural network ensembles | Vetrov D.P. | [Report](https://github.com/vshokorov/power_laws_deep_ensembles/blob/main/reports/VKR_maga_v1.pdf) [Code](https://github.com/vshokorov/power_laws_deep_ensembles) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :------------------- | :---------------------------------------------------------------------------------------------- | :------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Mariya Gorpinich | Metaparameter optimization in knowledge distillation | Bakhteev O.Yu. | [Code](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis), [Slides](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/slides/Gorpinich2021DistillingKnowledge_slides.pdf), [Paper](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/Gorpinich2021DistillingKnowledge.pdf) | +| Vyacheslav Gorchakov | Importance Sampling Approach to Chance-Constrained DC Optimal Power Flow | Maximov Y.V. | [Paper](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/Gorchakov_BS_Thesis_text.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/tree/master/code), [Slides](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/BS_thesis_slides.pdf) | +| Antonina Kurdyukova | Dimensionality reduction of the phase space in canonical correlation analisys | Strijov V.V., Isachenko R.V. | [Code](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/blob/master/code/ccm_accelerometer.ipynb), [Slides](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/blob/master/slides/BSThesis_Kurdyukova_Slides.pdf), [Paper](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/blob/master/docs/BSThesis_Kurdyukova__Copy_-3.pdf) | +| Anton Pilkevich | Optimization of the criterion given by the neural network model in the text detoxification task | [Strijov V.V.](http://www.ccas.ru/strijov/) (Popov A.S.) | [Code](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis), [Slides](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/pres.pdf),[Paper](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/main.pdf) | +| Konstantin Yakovlev | Selection of concordant architectures with complexity control | Bakhteev O.Y. | [Paper](https://easychair.org/publications/preprint_open/H5MC) [Code](https://github.com/Intelligent-Systems-Phystech/DARTS-CC), [Slides](https://github.com/Intelligent-Systems-Phystech/Yakovlev-BS-Thesis/raw/master/slides/main.pdf) | +| Khristolyubov Maxim | Approximation of the phase trajectory of the time series | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper]() [Code](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/tree/main/code), [Slides](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/tree/main/slides) | + +### 2021 Fall + +#### PhD Students + +| PhD Student | Year | PhD Topic | Advisor | Links | +| :---------------- | :--: | :------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Andrey Grabovoy | 1 | A prior distribution of parameters in problems of choosing deep learning models | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/andriygav/PhDThesis/blob/master/thesis/Grabovoy2021PhDThesis.pdf), [Code](https://github.com/andriygav/PhDThesis), [Slides](https://github.com/andriygav/PhDThesis/blob/master/slides/Grabovoy2021PhDSlides.pdf) | +| Alina Samokhina | 1 | Continuous time representation for signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://www.overleaf.com/read/dmtgkgpnnjkg) | +| Tamaz Gadaev | 1 | Multilinear model choice in forecasting problem | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://www.overleaf.com/read/bfrhvjqybbqw) | +| Vasilii Novitskii | 1 | New Bounds for One-point Oracle in Stochastic Gradient-free Optimization | [Gasnikov A.V.](http://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=27590) | [Paper 1](https://arxiv.org/abs/2101.03821), [Paper 2](https://arxiv.org/abs/2103.00321), [Slides](https://drive.google.com/file/d/1XLs65z9Yir-h4kgtQK-7ccqIYKL4g4U9/view?usp=sharing), [Code](https://drive.google.com/file/d/1RUPsCpTCSvPb9WYWTK8ybV89Z1RKzudj/view?usp=sharing) | +| Vasiliy Alekseev | 2 | Incompleteness and Instability of Topic Models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://www.sciencedirect.com/science/article/pii/S0169023X21000483), [Code](https://github.com/machine-intelligence-laboratory/OptimalNumberOfTopics), [Slides1](http://www.machinelearning.ru/wiki/images/f/fa/Alekseev2021TopicBankMMROSlides.pdf), [Slides2](http://www.machinelearning.ru/wiki/images/2/29/Alekseev2021TopicBankMIPTSlides.pdf) | +| Polina Potapova | 2 | Topic modeling for multilingual topic search | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Paper](https://github.com/Guince/PhDReports/blob/main/Neuroclustering.pdf) | +| Petr Ostroukhov | 3 | Tensor methods for optimization of convex functions | [Gasnikov A.V.](https://scholar.google.ru/citations?hl=ru&authuser=1&user=AmeE8qkAAAAJ) | [Paper](https://arxiv.org/abs/2012.15595) | +| Denis Kuznetsov | 3 | Neural network models of dialogue on general topics | [Burtsev M.S.](https://scholar.google.ru/citations?hl=ru&user=t_PLQakAAAAJ) | [Paper](https://aclanthology.org/2021.codi-main.4/) | +| Kamil Safin | 3 | Intrinsic methods for plagiarised texts detection | Chehovich Y.V. | [Paper](https://link.springer.com/chapter/10.1007/978-3-030-92711-0_7) | +| Ilia Zharikov | 4 | Neural network methods for document image recognition | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | Paper | + +#### Master's Students (2nd year) + +| Student | Thesis topic | Advisor | Links | +| :------------------- | :---------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Petr Mokrov | Wasserstein gradient flows: modeling and applications | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ&hl=en) | [Paper](https://openreview.net/forum?id=nlLjIuHsMHp), [Code](https://github.com/PetrMokrov/Large-Scale-Wasserstein-Gradient-Flows), [Slides](https://drive.google.com/file/d/1t0lYIeBDujZLmkbtXqwLe-_nkOKf6kzj/view?usp=sharing) | +| Denis Tikhonov | Model selection for quasiperiodic time series forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Code](https://github.com/Denis-Tihonov/Spherical_Harmonics_parametrisation), [Slides](https://github.com/Denis-Tihonov/Spherical_Harmonics_parametrisation/blob/main/slides/Tikhonov2021ApproximatinPresentation.pdf) | +| Alexey Grigorev | Regularization of neural layer via construction of frame in parameter space | [Gneushev A.N.](https://scholar.google.com/citations?hl=en&user=sjlY2q8AAAAJ) | [Slides](https://drive.google.com/uc?id=19rg9DegVH_rQRsjpasatkpMCMpha3kDt&export=download), [Code](https://github.com/formica-rufa/WO); [Paper](https://drive.google.com/uc?id=1lVVXaKIkzWixxp8KK-imWGnvt0JDt1Is&export=download) | +| Natalia Varenik | Building a connectivity map of functional groups in the problem of decoding brain signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://github.com/Natalia-Varenik/MasterThesis/blob/main/doc/Graphs_for_BCI-5.pdf) [Slides](https://github.com/Natalia-Varenik/MasterThesis/blob/main/slides/master_thesis_presentation.pdf) [Code](https://github.com/Natalia-Varenik/MasterThesis/tree/main/code) | +| Severilov Pavel | Differential analysis of phase spaces in the problem of decoding signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Slides](https://github.com/severilov/master-thesis/blob/main/pres/Severilov2022MasterThesisPres.pdf) [Code](https://github.com/severilov/master-thesis/tree/main/code) | +| Panchenko Sviatoslav | Bilinearity of geometric product for the task of signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Slides](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/notes/GeometricAlgebraForDecoding.pdf) | +| Grishanov Alexey | Application of Reinforcement Learning for recommendation system personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Slides](https://drive.google.com/file/d/1AKAz5hTMEd0ig9ob_WvJwluz0O5Zk0A2/view?usp=sharing), [Сode](https://github.com/shashist/recsys-rl) | +| Kolesov Aleksandr | Adversarial approach for transfer learning | [Bahteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=Участник:Oleg_Bakhteev) | [Paper](https://drive.google.com/file/d/1wazibI5TtWUiOn3k6es5YdXasS3XeMeG/view?usp=sharing), [Slides](https://docs.google.com/presentation/d/10BEdMzxupJbj7xkb-20MPluqXQ2qTK-ojpaXmtA8E9s/edit?usp=sharing), [Сode](https://github.com/Intelligent-Systems-Phystech/HeterogenKD/tree/main/code/notebooks) | + +#### Master's Students (1st year) + +| Student | Topic | Advisor | Links | +| :------------------ | :------------------------------------------------------------------ | :---------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Rustem Islamov | Second Order Methods for Federated Learning | [Richtarik P](https://richtarik.org/), [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](https://arxiv.org/abs/2106.02969), [Code](https://github.com/Intelligent-Systems-Phystech/Islamov-Rustem/tree/main/Master%20Thesis/Code), [Slides](https://github.com/Intelligent-Systems-Phystech/Islamov-Rustem/blob/main/Master%20Thesis/Presentation/Islamov2021Presentation.pdf) | +| Grebenkova Olga | Automated detection of focal cortical dysplasia | [Burnaev E](https://faculty.skoltech.ru/people/evgenyburnaev) | [Paper](http://www.mathnet.ru/links/bf98d4af33339019591a1b13329cae49/ia710.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/VarHyperNet), [Slides](https://github.com/Intelligent-Systems-Phystech/Grebenkova-BS-Thesis/blob/main/Grebenkova2020OptimizationSlides.pdf) | +| Safiullin Robert | Substance properties analysis based on its SERS spectra | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Report](https://github.com/roberts2510/SafiullinMSThesis/blob/main/Safiullin_report.pdf), [Slides](https://github.com/roberts2510/SafiullinMSThesis/blob/main/Slides/SafiullinMS_slides_1.pdf) | +| Pankratov Viktor | Topic balancing of topic models | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Report](https://github.com/PankratovViktor/Pankratov_BS_Thesis/blob/main/Pankratov_Report_S9_2021.pdf),[Code](https://github.com/PankratovViktor/Pankratov_BS_Thesis/tree/main/pyartm) | +| Filatov Andrei | Task Discovery | [Victor Lempitsky](https://faculty.skoltech.ru/people/victorlempitsky) [Strijov V.V.](http://www.ccas.ru/strijov/) | [Report]() | +| Bishuk Anton | Controlled graph generation using the variational autoencoder model | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Report](https://github.com/Intelligent-Systems-Phystech/Bishuk-MS-Thesis-public/blob/master/%D0%9E%D0%B1%D0%B7%D0%BE%D1%80-%D0%BB%D0%B8%D1%82%D0%B5%D1%80%D0%B0%D1%82%D1%83%D1%80%D1%8B.pdf) | +| Shokorov Viacheslav | Bootstrapping of neural network ensembles | Vetrov D.P. | [Report](https://github.com/vshokorov/power_laws_deep_ensembles/blob/main/reports/VKR_maga_v1.pdf) [Code](https://github.com/vshokorov/power_laws_deep_ensembles) | + +#### Bachelor's Students (4th year) + +| Student | Thesis topic | Advisor | Links | +| :------------------- | :----------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| Antonina Kurdyukova | Phase detection of human motions with signals of wearable devices | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Paper](), [Code](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/tree/master/code), [Slides]() | +| Anton Pilkevich | Clustering of news text messages based on polar opinions | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | | +| Gorpinich Mariya | Metaparameter optimization in knowledge distillation | [Bakhteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Oleg_Bakhteev) | [Paper](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/docs/Gorpinich2021DistillingKnowledge.pdf), [Code](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis), [Slides](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/docs/slides/Gorpinich2021DistillingKnowledgeSlides.pdf) | +| Vyacheslav Gorchakov | Importance Sampling Approach to Chance-Constrained DC Optimal Power Flow | Maximov Y.V. | [Paper](https://arxiv.org/abs/2111.11729), [Code](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/tree/master/code) | +| Konstantin Yakovlev | Selection of concordant architectures with complexity control | Bakhteev O.Y. | [Code](https://github.com/Intelligent-Systems-Phystech/DARTS-CC), [Slides](https://github.com/Intelligent-Systems-Phystech/Yakovlev-BS-Thesis/raw/master/slides/main.pdf) | diff --git a/_i18n/en/paper_guidelines.md b/_i18n/en/paper_guidelines.md index 66de62d3..09db6a8f 100644 --- a/_i18n/en/paper_guidelines.md +++ b/_i18n/en/paper_guidelines.md @@ -1,19 +1,116 @@ -# Standards -* [Theses defence in MIPT](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vypusknoy_kvalikafitsionnoy_rabote_studentov_mfti_49_1_ot_21_01) -* [Candidate defence law](http://www.consultant.ru/document/cons_doc_LAW_152458/3accc895434fd7ce6fd7d8f8a570ab064e960560/) +## Paper Writing and Defense Guidelines -# Guidelines -* [ML-wiki: guide to write articles](http://www.machinelearning.ru/wiki/index.php?title=%D0%9D%D0%B0%D0%BF%D0%B8%D1%81%D0%B0%D0%BD%D0%B8%D0%B5_%D0%BE%D1%82%D1%87%D1%91%D1%82%D0%BE%D0%B2_%D0%B8_%D1%81%D1%82%D0%B0%D1%82%D0%B5%D0%B9_%28%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%86%D0%B8%D0%B8%29) -* [ML-wiki: paper submission to Russian journal](http://www.machinelearning.ru/wiki/index.php?title=%D0%90%D0%B2%D1%82%D0%BE%D0%BC%D0%B0%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%B8_%D1%81%D1%82%D0%B0%D0%BD%D0%B4%D0%B0%D1%80%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%BD%D0%B0%D1%83%D1%87%D0%BD%D1%8B%D1%85_%D0%B8%D1%81%D1%81%D0%BB%D0%B5%D0%B4%D0%BE%D0%B2%D0%B0%D0%BD%D0%B8%D0%B9_%28%D0%BF%D1%80%D0%B0%D0%BA%D1%82%D0%B8%D0%BA%D0%B0%2C_%D0%92.%D0%92._%D0%A1%D1%82%D1%80%D0%B8%D0%B6%D0%BE%D0%B2%29#.D0.9A.D0.B0.D0.BA_.D0.BF.D0.BE.D0.B4.D0.B0.D1.82.D1.8C_.D1.81.D1.82.D0.B0.D1.82.D1.8C.D1.8E_.D0.B2_.D1.80.D1.83.D1.81.D1.81.D0.BA.D0.B8.D0.B9_.D0.B6.D1.83.D1.80.D0.BD.D0.B0.D0.BB) -* [ML-wiki: paper submission to international journal](http://www.machinelearning.ru/wiki/index.php?title=%D0%90%D0%B2%D1%82%D0%BE%D0%BC%D0%B0%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%B8_%D1%81%D1%82%D0%B0%D0%BD%D0%B4%D0%B0%D1%80%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%BD%D0%B0%D1%83%D1%87%D0%BD%D1%8B%D1%85_%D0%B8%D1%81%D1%81%D0%BB%D0%B5%D0%B4%D0%BE%D0%B2%D0%B0%D0%BD%D0%B8%D0%B9_%28%D0%BF%D1%80%D0%B0%D0%BA%D1%82%D0%B8%D0%BA%D0%B0%2C_%D0%92.%D0%92._%D0%A1%D1%82%D1%80%D0%B8%D0%B6%D0%BE%D0%B2%29#.D0.9A.D0.B0.D0.BA_.D0.BF.D0.BE.D0.B4.D0.B0.D1.82.D1.8C_.D1.81.D1.82.D0.B0.D1.82.D1.8C.D1.8E_.D0.B2_.D0.BC.D0.B5.D0.B6.D0.B4.D1.83.D0.BD.D0.B0.D1.80.D0.BE.D0.B4.D0.BD.D1.8B.D0.B9_.D0.B6.D1.83.D1.80.D0.BD.D0.B0.D0.BB) -* ["My first scientific paper" course](../../course/automation_scientific_research/index.html) -* [PhD guide (valid: March 2022)](https://docs.google.com/document/d/1TzV5e7-7WhPwLzgyWidYykx2HlXYs0g4pBrr28dpbrk/edit?usp=sharing) +On this page, you will find guidelines for writing scientific papers, choosing publication venues, and defending your thesis work at the Intelligent Systems Department. -# Where to sumbit -* [SJR journal index](https://www.scimagojr.com/) -* [ex-Guide2Research: list of conferences and journals with statistics](https://research.com/) -* [Conference rankings](http://www.conferenceranks.com/) -* [Main ML conferences and workshops (updates every month)](https://tinyurl.com/bahleg-conf) -* [Main ML journals (updates every 6 months)](https://tinyurl.com/bahleg-journals) +### Guidelines for Writing a Scientific Paper +- [Course "My First Scientific Paper" (m1p)](https://m1p.org/index.php/My_first_scientific_paper) +- [Writing Reports and Articles for Students and Postgraduates](http://www.machinelearning.ru/wiki/index.php?title=%D0%9D%D0%B0%D0%BF%D0%B8%D1%81%D0%B0%D0%BD%D0%B8%D0%B5_%D0%BE%D1%82%D1%87%D1%91%D1%82%D0%BE%D0%B2_%D0%B8_%D1%81%D1%82%D0%B0%D1%82%D0%B5%D0%B9_%28%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%86%D0%B8%D0%B8%29) +- [ICML Guidelines for ML Papers](https://icml.cc/Conferences/2002/craft.html) +- [Nature Recommendations for Any Type of Paper](https://www.nature.com/scitable/topicpage/scientific-papers-13815490/#) +### Choosing a Publication Venue and Submission Process + +- [Where and How to Submit Your Work from m1p](https://m1p.org/index.php/Week_10) +- [SJR Journal Index](https://www.scimagojr.com/) +- [International Conference Rankings](http://www.conferenceranks.com/) +- [Major ML Conferences and Workshops (updated monthly)](https://tinyurl.com/bahleg-conf) +- [Major ML Journals (updated semi-annually)](https://tinyurl.com/bahleg-journals) + +### On Defending Thesis Work at the Department + +#### (Pre-)Defense Checklist + +1. Thesis, slides, and code are in your repository _under the_ [_department organization_](https://github.com/intsystems/) +2. A link to your work is in the [theses table]({{ site.baseurl }}/materials/thesis) + +#### Documents Required for Defense + +1. Supervisor's review +2. Antiplagiat check report +3. External reviewer's report (for Master's degrees) + +#### Scope and Content of the Final Qualifying Work (FQW) + +For the recommended scope, please read the [MIPT Regulations on FQW Defense](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vypusknoy_kvalikafitsionnoy_rabote_studentov_mfti_49_1_ot_21_01). A mandatory volume is not defined. + +Your results, presented for defense, are important. They should be formatted as a scientific paper (two for Master's degrees). Publication of these papers in a peer-reviewed journal signifies the acceptance of your results by the scientific community. Together with a formal introduction, they will constitute the recommended volume. + +When presenting: + +1. Describe the conditions and your assumptions regarding the problem being solved: spaces, algebraic structures, statistical hypotheses. +2. Justify the solution to the problem, indicate the properties of the solution. +3. Formulate your results as strict statements. +4. Analyze the obtained solution and results. + +Avoid describing your solution in the style of "how I do this step by step". It is more important to describe "why I am doing this" and "what contribution this makes to solving the problem". + +Not needed: + +1. Copying diagrams and illustrations from other papers. +2. Automatically generated text. + +Others' material and co-authors' material: + +1. Present it with citations, exactly to the extent required to explain your personal results. +2. Rephrase and improve others' text and diagrams. + +#### Defense FAQ + +1. **Can I edit the thesis text after the pre-defense?** – Yes, and you should, even after the defense. The thesis results will be used primarily by you. But if the version presented at the pre-defense requires significant revision, it raises questions about the quality of the work and the assessment. +2. **Where can I find the formal requirements for the FQW?** – Be sure to read the [Defense Regulations](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vkr). +3. **What time are the pre-defense and defense?** – Pre-defenses at 10:00, defenses at 13:00. +4. **Online or offline?** – Pre-defenses online, defenses offline at Vavilova st., 42, room 355. Access control by list, check this separately. +5. **Do I need to print the FQW for the defense?** – Yes. It is polite towards the committee to provide a paper copy of the thesis text. +6. **What is the defense format?** – 7-minute presentation + 5 minutes for questions. Keep track of time! +7. **When do I need to upload the FQW?** – The department does not know when you need to upload the FQW to your personal account. But you must upload the thesis and all other links to the [department page]({{ site.baseurl }}/materials/thesis) by the pre-defense. +8. **When is the supervisor's review needed?** By the defense. Bring it with you. Master's students – same with the reviewer's report. +9. **When is the plagiarism report needed?** By the defense. Bring it with you. In case of a high percentage of borrowings, the report must be signed by the supervisor. +10. **Is a reviewer's report needed?** – No for Bachelors, yes for Masters. +11. **When do I need to upload the reviewer's report?** By the defense. Bring it with you (if the reviewer is not from MIPT, their signature must be certified at their place of work). +12. **What are the requirements for the reviewer?** – See clause 5 of the Regulations. +13. **Are scanned documents sufficient?** – No, originals are needed. +14. **Do I need to upload all papers to my MIPT personal account?** – Only the thesis text with a Russian abstract. + - Upload the text to Personal Account > Academic Process > FQW Upload, + - Check it with the Plagiarism system, + - Since your work was previously published by you, the Plagiarism system should find it (and that's great, as it indicates the scientific community is familiar with it), + - Ask your supervisor to mark that your work was previously published, + - For the same reason, do not add generated text to the thesis (it's unnecessary – we have no volume requirements, but we do have quality requirements), + - After that, upload the Russian abstract and thesis text to the EBS (button below), + - It is important to do this no later than two days before the defense (if defense is on the 25th, upload on the 22nd). +15. **Language of the text** – We have not found any language requirements in the FQW Defense Regulations. Therefore, given that your work is published in a journal, the decision is left to you. + +#### Standards + +- [MIPT FQW Defense Regulations](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vypusknoy_kvalikafitsionnoy_rabote_studentov_mfti_49_1_ot_21_01) +- [Regulations on Awarding Academic Degrees in the Russian Federation](http://www.consultant.ru/document/cons_doc_LAW_152458/3accc895434fd7ce6fd7d8f8a570ab064e960560/) + + diff --git a/_i18n/en/scholarship.md b/_i18n/en/scholarship.md index c6a30f1d..a99ea419 100644 --- a/_i18n/en/scholarship.md +++ b/_i18n/en/scholarship.md @@ -1,3 +1,24 @@ -### Scholarship Info +## K.V. Rudakov Academic Research Scholarship -[Related information here.](https://intsystems.github.io/ru/materials/scholarship/) +The scholarship supports 2–4 year Bachelor’s students and 1–2 year Master’s students of the Department of Intelligent Data Analysis who are conducting research in applied mathematics, including machine learning, data analysis, and other branches of mathematics. The scholarship is awarded on a monthly basis. + +### Selection Criteria + +- The likelihood of completing high-quality research work on time. +- The expected contribution to the studied problem or task solution. +- Achievements in teaching and contributions to the development of the Department. + +### Application Deadlines + +- Fall deadline: September 2 +- Spring deadline: February 3 +- Submit your application [here, via Google Form](https://forms.gle/4TQrMp4mWPV8CxcE9) +- [Applications from previous years and Scholarship Regulations](images/NIR_KV_Rudakov_scholarship.pdf) + +### Scholarship Committee + +Representatives from [Antiplagiat](https://antiplagiat.ru/), [ProCompliance](https://www.forecsys.ru/%D0%BE-%D0%BA%D0%BE%D0%BC%D0%BF%D0%B0%D0%BD%D0%B8%D0%B8/), and [Forecsys](https://forecsys.ru/) + +### Application Template + +Full name of the student; average GPA (from the student’s portal); full name and academic degree of the research advisor; research topic; abstract; expected outcome (preferably specify both the actual and formal result — e.g., the target journal for publication or another form of result presentation); teaching and contribution to the Department of Intelligent Systems (participation and plans); link to additional materials (if any, e.g., preliminary research results or outcomes from the previous semester). diff --git a/_i18n/en/seminars.md b/_i18n/en/seminars.md index 7af8281f..10532dc1 100644 --- a/_i18n/en/seminars.md +++ b/_i18n/en/seminars.md @@ -1,200 +1,202 @@ -# Meetings and seminars +## Meetings -### Vadim Strijov's seminar: research paper for the semester. Risks and results in machine learning - - +This page contains links to recent seminars, meetings with alumni, PhD defences, Bachelor's and Master's pre-defences and defences of students of the Intelligent Systems Department, MIPT. +### Bachelor's and Master's defences -### Meetinig with Nikita Zhivotovskiy, alumnus of the MIPT Department of Intelligent Systems, 2013 +#### Bachelor's pre-defence, 2025 -**Date:** 21.04.2022 +**Students**: Egor Zadvornov, Sergey Firsov, Ilya Stepanov, Alexey Rebrikov, Fanis Khafizov, Denis Rubtsov, Ivan Papay, Muhammadsharif Nabiev, Altay Eynullayev, Fedor Sobolevsky, Vadim Kasiuk, Vladislav Meshkov, Anastasia Linich, Gleb Karpeev -**Guest:** [Nikita Zhivotovskiy](https://www.linkedin.com/in/nikita-zhivotovskiy-06816597/) is a candidate of physical and mathematical sciences. He is a researcher at Google Research, Zürich. + - -

-### Meeting with Kirill Pavlov, alumnus of the MIPT Department of Intelligent Systems, 2012 +#### Master's pre-defences, 2025 -**Date:** 27.03.2022 +**Students**: Nikita Kornilov, Galina Boeva, Eduard Vladimirov, Arina Chumachenko, German Gritsai, Kseniia Petrushina, Ildar Khabutdinov, Marat Khusainov -**Guest:** [Kirill Pavlov](https://www.linkedin.com/in/pavlov99/) is an alumnus, 2012, researcher. + - -

+#### Bachelor's pre-defence, 2024 -### Meeting with Roman Sologub, alumnus of the MIPT Department of Intelligent Systems, 2010 +**Students**: Petr Babkin, Aleksandr Bogdanov, Andrey Veprikov, Daniil Dorin, Igor Ignashin, Nikita Kiselev, Matvei Kreinin, Andrey Veprikov, Maria Nikitina, Nikita Okhotnikov, Kirill Semkin, Aleksandr Terentiev, Anastasia Voznyuk, Anna Remizova -**Date:** 11.03.2022 + -**Guest:** [Roman Sologub](https://www.linkedin.com/in/roman-sologub-phd-86038648/) +
-Roman Sologub is a candidate of physical and mathematical sciences. He is a financial analyst from London. +#### Master's pre-defences, 2024 +**Students**: Konstantin Yakovlev, Polina Barabanschikova, Roman Klypa, Grigoriy Ksenofontov, Emil Alkin, Maria Kovaleva, Aleksandr Tolmachev - -
-
+ -### Meeting with alumni of the MIPT Department of Intelligent Systems, 2013 +
-**Date:** 17.02.2022 +#### Bachelor's defences, 2022 -**Guests:** [Mikhail Kuznetsov](https://scholar.google.com/citations?user=w1CmemUAAAAJ&hl=ru&oi=ao), [Nikita Ivkin](https://scholar.google.com/citations?user=wHAYz5wAAAAJ&hl=ru&oi=ao) +**Students**: Konstantin Yakovlev, Maria Gorpinich, Antonina Kurdyukova, Vyacheslav Gorсhakov, Anton Pilkevich, Maxim Khristolybov -The alumni of the department are engaged in research in the field of machine learning and data analysis in large commercial companies. - -* Mikhail Kuznetsov: candidate of physical and mathematical sciences, MIPT, researcher at Yahoo and Amazon -* Nikita Ivkin: PhD Johns Hopkins University, researcher at Amazon + - -

-### Prior Distribution of Parameters in Deep Learning Model Selection Problem - -**Date:** 24.01.2022 +#### Master's defences, 2022 -**Speaker:** [Andrey Grabovoy](../../people/grabovoy_av) +**Students**: Petr Mokrov, Natalia Varenik, Alexey Grigoriev, Sviatoslav Panchenko, Pavel Severilov, Denis Tikhonov, Alexander Kolesov, Alexey Grishanov -The seminar is devoted to deep learning model distillation. We discuss the alignment of the structures of teacher and student models. Bayesian inference is used to optimize student parameters. We give an examples of distillation fully connected and recurrent neural networks as models of a teacher and a student. + - -

-### Dimension Reduction in Signal Decoding Problems - -**Date:** 13.12.2021 +#### Bachelor's defences, 2021 -**Speaker:** [Roman Isachenko](../../people/isachenko_rv) - -The seminar is devoted to the problem of reducing the dimension of space when solving the problem of signal decoding. The decoding process consists in restoring the relationship between two heterogeneous datasets. A feature of the problem is the presence of hidden dependencies not only in the source signals, but also in the target ones. We propose dimension reduction methods that allow using dependencies in the source and target spaces. +**Students**: Drmitriy Kovalev, Anton Bishuk, Kirill Vayser, Olga Grebenkova, Ruslan Gunaev, Vladimir Zholobov, Rustem Islamov, Victor Pankratov, Nikolay Saveliev, Andrey Filatov, Anastasia Filippova, Aleksandra Khar, Vyacheslav Shokorov, Tagir Sattarov + - -

-### Uncertainty, Out-of-distribution detection for NNs +#### Master's defences, 2021 -**Date:** 8.07.2021 +**Students**: Egor Gladin, Andrey Grabovoy, Vadim Kislinskiy, Evgeniy Kozlinskiy, Grigory Malinovsky, Egor Shulgin, Vasiliy Novitskiy, Anna Rogozina, Nikita Pletnev, Alina Samokhina, Tamaz Gadaev, Gleb Morgachev -**Speaker:** [Maxim Panov](https://faculty.skoltech.ru/people/maximpanov) + -Maxim Panov (Associate Professor at Skoltech) will tell at the seminar what Uncertainty is in Bayesian inference. +### PhD defences - -

-# PhD defences - -### Roman Isachenko, 2021 +#### Roman Isachenko, 2021 [Link to thesis](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/31-isachenko/ds05_31-isachenko_main.pdf?18) -
+
-### Oleg Bakhteev, 2020 + +#### Oleg Bakhteev, 2020 + [Link to thesis](https://frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/26-bahteev/ds05-26-bahteev_main.pdf?28) -
+
-### Anastasia Motrenko, 2019 +#### Anastasia Motrenko, 2019 + [Link to thesis](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/23-motrenko/ds05_23-motrenko_main.pdf?683) -
+
-### Alexander Aduenko, 2017 +#### Alexander Aduenko, 2017 + [Link to thesis](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/11-aduenko/11-Aduenko_main.pdf?626) -
+
-### Arsentiy Kuzmin, 2017 + +#### Arsentiy Kuzmin, 2017 + [Link to thesis](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/08-kuzmin/008-kuzmin_main-txt.pdf?809) -
-
-# Master's and Bachelor's defences -### Bachelor's pre-defence, 2025 +### Meetings and seminars -**Students**: Egor Zadvornov, Sergey Firsov, Ilya Stepanov, Alexey Rebrikov, Fanis Khafizov, Denis Rubtsov, Ivan Papay, Muhammadsharif Nabiev, Altay Eynullayev, Fedor Sobolevsky, Vadim Kasiuk, Vladislav Meshkov, Anastasia Linich, Gleb Karpeev +This page contains links to recent seminars, meetings with alumni, PhD defences, Master's and Bachelor's pre-defences and defences of students of the Intelligent Systems Department, MIPT. - +
+ +#### Vadim Strijov's seminar: research paper for the semester. Risks and results in machine learning + + -

-### Master's pre-defences, 2025 +#### Meetinig with Nikita Zhivotovskiy, alumnus of the MIPT Department of Intelligent Systems, 2013 -**Students**: Nikita Kornilov, Galina Boeva, Eduard Vladimirov, Arina Chumachenko, German Gritsai, Kseniia Petrushina, Ildar Khabutdinov, Marat Khusainov +**Date:** 21.04.2022 - +**Guest:** [Nikita Zhivotovskiy](https://www.linkedin.com/in/nikita-zhivotovskiy-06816597/) is a candidate of physical and mathematical sciences. He is a researcher at Google Research, Zürich. + + -

-### Bachelor's pre-defence, 2024 +#### Meeting with Kirill Pavlov, alumnus of the MIPT Department of Intelligent Systems, 2012 -**Students**: Petr Babkin, Aleksandr Bogdanov, Andrey Veprikov, Daniil Dorin, Igor Ignashin, Nikita Kiselev, Matvei Kreinin, Andrey Veprikov, Maria Nikitina, Nikita Okhotnikov, Kirill Semkin, Aleksandr Terentiev, Anastasia Voznyuk, Anna Remizova +**Date:** 27.03.2022 - +**Guest:** [Kirill Pavlov](https://www.linkedin.com/in/pavlov99/) is an alumnus, 2012, researcher. + + -

-### Master's pre-defences, 2024 +#### Meeting with Roman Sologub, alumnus of the MIPT Department of Intelligent Systems, 2010 -**Students**: Konstantin Yakovlev, Polina Barabanschikova, Roman Klypa, Grigoriy Ksenofontov, Emil Alkin, Maria Kovaleva, Aleksandr Tolmachev +**Date:** 11.03.2022 - +**Guest:** [Roman Sologub](https://www.linkedin.com/in/roman-sologub-phd-86038648/) + +Roman Sologub is a candidate of physical and mathematical sciences. He is a financial analyst from London. + + -

+#### Meeting with alumni of the MIPT Department of Intelligent Systems, 2013 -### Bachelor's defences, 2022 -**Students**: Konstantin Yakovlev, Maria Gorpinich, Antonina Kurdyukova, Vyacheslav Gorсhakov, Anton Pilkevich, Maxim Khristolybov +**Date:** 17.02.2022 - -
-
+**Guests:** [Mikhail Kuznetsov](https://scholar.google.com/citations?user=w1CmemUAAAAJ&hl=ru&oi=ao), [Nikita Ivkin](https://scholar.google.com/citations?user=wHAYz5wAAAAJ&hl=ru&oi=ao) -### Master's defences, 2022 -**Students**: Petr Mokrov, Natalia Varenik, Alexey Grigoriev, Sviatoslav Panchenko, Pavel Severilov, Denis Tikhonov, Alexander Kolesov, Alexey Grishanov +The alumni of the department are engaged in research in the field of machine learning and data analysis in large commercial companies. - +- Mikhail Kuznetsov: candidate of physical and mathematical sciences, MIPT, researcher at Yahoo and Amazon +- Nikita Ivkin: PhD Johns Hopkins University, researcher at Amazon + + -

-### Bachelor's defences, 2021 -**Students**: Drmitriy Kovalev, Anton Bishuk, Kirill Vayser, Olga Grebenkova, Ruslan Gunaev, Vladimir Zholobov, Rustem Islamov, Victor Pankratov, Nikolay Saveliev, Andrey Filatov, Anastasia Filippova, Aleksandra Khar, Vyacheslav Shokorov, Tagir Sattarov +#### Prior Distribution of Parameters in Deep Learning Model Selection Problem + +**Date:** 24.01.2022 + +**Speaker:** [Andrey Grabovoy](../../people/grabovoy_av) + +The seminar is devoted to deep learning model distillation. We discuss the alignment of the structures of teacher and student models. Bayesian inference is used to optimize student parameters. We give an examples of distillation fully connected and recurrent neural networks as models of a teacher and a student. + + - -

+#### Dimension Reduction in Signal Decoding Problems + +**Date:** 13.12.2021 +**Speaker:** [Roman Isachenko](../../people/isachenko_rv) -### Master's defences, 2021 -**Students**: Egor Gladin, Andrey Grabovoy, Vadim Kislinskiy, Evgeniy Kozlinskiy, Grigory Malinovsky, Egor Shulgin, Vasiliy Novitskiy, Anna Rogozina, Nikita Pletnev, Alina Samokhina, Tamaz Gadaev, Gleb Morgachev +The seminar is devoted to the problem of reducing the dimension of space when solving the problem of signal decoding. The decoding process consists in restoring the relationship between two heterogeneous datasets. A feature of the problem is the presence of hidden dependencies not only in the source signals, but also in the target ones. We propose dimension reduction methods that allow using dependencies in the source and target spaces. + + - -

+#### Uncertainty, Out-of-distribution detection for NNs +**Date:** 8.07.2021 + +**Speaker:** [Maxim Panov](https://faculty.skoltech.ru/people/maximpanov) +Maxim Panov (Associate Professor at Skoltech) will tell at the seminar what Uncertainty is in Bayesian inference. + + diff --git a/_i18n/en/templates.md b/_i18n/en/templates.md new file mode 100644 index 00000000..4fc860fb --- /dev/null +++ b/_i18n/en/templates.md @@ -0,0 +1,7 @@ +## Templates + +Here we collect useful templates for writing papers, reports, and theses. + +- [intsystems-slides](https://github.com/kisnikser/intsystems-slides): Collection of slides templates for reports and theses +- [m1p-template](https://github.com/kisnikser/m1p-template): Simple and clean template for [My First Scientific Paper]({{ site.baseurl }}/course/automation_scientific_research) project +- [research-template](https://github.com/kisnikser/research-template): Minimalistic research template diff --git a/_i18n/en/thesis.md b/_i18n/en/thesis.md index 85918b5a..47980d5d 100644 --- a/_i18n/en/thesis.md +++ b/_i18n/en/thesis.md @@ -1,137 +1,129 @@ +## Theses + +This page contains links to recent theses of students of the Intelligent Systems Department, MIPT. + ### 2025 #### Master's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -|Kornilov Nikita|Optimal Flow Matching: новый подход к генеративному моделированию и оптимальному транспорту|[Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru) |[Project](https://github.com/intsystems/Kornilov_MS_Thesis)|[Thesis](https://github.com/intsystems/Kornilov_MS_Thesis/blob/master/paper/Kornilov_Nikita_Thesis_IAD_v3.pdf)|[Slides](https://github.com/intsystems/Kornilov_MS_Thesis/blob/master/slides/Корнилов_Слайды_защиты_2025%20final.pdf)| -| Boeva Galina | Efficient aggregation by labels for the problem of event sequences | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Project](https://github.com/intsystems/Boeva-MS-Thesis) | [Thesis](https://github.com/intsystems/Boeva-MS-Thesis/blob/master/paper/thesis_master_2025.pdf) | [Slides](https://github.com/intsystems/Boeva-MS-Thesis/blob/master/slides/%D0%B7%D0%B0%D1%89%D0%B8%D1%82%D0%B0_2025.pdf)| -| Vladimirov Eduard | Причинно-ориентированное снижение размерности для анализа данных нейроинтерфейсов | [Strijov V.V](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master) | [Thesis](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/paper/Vladimirov2024GenerativeCIPaper.pdf) | [Slides](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/slides/Vladimirov2024GenerativeCISlides.pdf)| -| Mikhailov Bair | Development of Machine Learning Methods for Radiology in Brain Evolution Research | [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Project](https://github.com/intsystems/Mikhailov-MS-Thesis) | [Thesis](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/slides/slides.pdf)| -| Chumachenko Arina | Preventing Overfitting in Subject-Driven Text-to-Image Diffusion: Regularization of Embedding and Attention Maps | [Oseledets I.V.](https://faculty.skoltech.ru/people/ivanoseledets) | [Project](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis) | [Paper](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/paper/Thesis_Chumachenko_MIPT.pdf) | [Slides](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/slides/Presentation_MIPT.pdf) | -| Gritsai German | Verification of artificially generated text fragments | [Grabovoy A. V.](https://andriygav.github.io/) | [Project](https://github.com/intsystems/Gritsai-MS-Thesis) | [Thesis](https://github.com/intsystems/Gritsai-MS-Thesis/blob/master/paper/MS_thesis.pdf) | [Slides](https://github.com/intsystems/Gritsai-MS-Thesis/blob/master/slides/mipt_nir%20(1).pdf)| -| Petrushina Kseniia | Detection of Multimodal Hallucinations Based on Internal Representations and Activations of Models | [Panchenko A. I.](https://new.skoltech.ru/persons/panchenko-aleksandr-ivanovich) | [Project](https://github.com/intsystems/Petrushina-MS-Thesis) | [Thesis](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/paper/Thesis2025Petrushina.pdf) | [Slides](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/slides/Slides2025Petrushina.pdf)| -| Khabutdinov Ildar | Исправление грамматических ошибок в домене низкоресурсных языков | [Grabovoy A. V.](https://andriygav.github.io/) | [Project](https://github.com/intsystems/Khabutdinov-MS-Thesis) | [Thesis](https://github.com/intsystems/Khabutdinov-MS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Khabutdinov-MS-Thesis/blob/master/slides/slides.pdf)| -| Marat Khusainov | Understanding the Plasticity of Neural Networks Employed in GFlowNets | Samsonov S.V. | [Project](https://github.com/intsystems/Khusainov-MS-Thesis/tree/master/) | [Thesis](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/slides/slides.pdf)| +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :----------------- | :--------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------- | :------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------- | +| Kornilov Nikita | Optimal Flow Matching: новый подход к генеративному моделированию и оптимальному транспорту | [Gasnikov A.V.](https://scholar.google.ru/citations?user=AmeE8qkAAAAJ&hl=ru) | [Project](https://github.com/intsystems/Kornilov_MS_Thesis) | [Thesis](https://github.com/intsystems/Kornilov_MS_Thesis/blob/master/paper/Kornilov_Nikita_Thesis_IAD_v3.pdf) | [Slides](https://github.com/intsystems/Kornilov_MS_Thesis/blob/master/slides/Корнилов_Слайды_защиты_2025%20final.pdf) | +| Boeva Galina | Efficient aggregation by labels for the problem of event sequences | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Project](https://github.com/intsystems/Boeva-MS-Thesis) | [Thesis](https://github.com/intsystems/Boeva-MS-Thesis/blob/master/paper/thesis_master_2025.pdf) | [Slides](https://github.com/intsystems/Boeva-MS-Thesis/blob/master/slides/%D0%B7%D0%B0%D1%89%D0%B8%D1%82%D0%B0_2025.pdf) | +| Vladimirov Eduard | Причинно-ориентированное снижение размерности для анализа данных нейроинтерфейсов | [Strijov V.V](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Vladimirov-MS-Thesis/tree/master) | [Thesis](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/paper/Vladimirov2024GenerativeCIPaper.pdf) | [Slides](https://github.com/intsystems/Vladimirov-MS-Thesis/blob/master/slides/Vladimirov2024GenerativeCISlides.pdf) | +| Mikhailov Bair | Development of Machine Learning Methods for Radiology in Brain Evolution Research | [Dylov D.V](https://faculty.skoltech.ru/people/dmitrydylov) | [Project](https://github.com/intsystems/Mikhailov-MS-Thesis) | [Thesis](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Mikhailov-MS-Thesis/blob/master/slides/slides.pdf) | +| Chumachenko Arina | Preventing Overfitting in Subject-Driven Text-to-Image Diffusion: Regularization of Embedding and Attention Maps | [Oseledets I.V.](https://faculty.skoltech.ru/people/ivanoseledets) | [Project](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis) | [Paper](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/paper/Thesis_Chumachenko_MIPT.pdf) | [Slides](https://github.com/arina-chumachenko/Chumachenko-MS-Thesis/blob/main/slides/Presentation_MIPT.pdf) | +| Gritsai German | Verification of artificially generated text fragments | [Grabovoy A. V.](https://andriygav.github.io/) | [Project](https://github.com/intsystems/Gritsai-MS-Thesis) | [Thesis](https://github.com/intsystems/Gritsai-MS-Thesis/blob/master/paper/MS_thesis.pdf) | [Slides]() | +| Petrushina Kseniia | Detection of Multimodal Hallucinations Based on Internal Representations and Activations of Models | [Panchenko A. I.](https://new.skoltech.ru/persons/panchenko-aleksandr-ivanovich) | [Project](https://github.com/intsystems/Petrushina-MS-Thesis) | [Thesis](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/paper/Thesis2025Petrushina.pdf) | [Slides](https://github.com/intsystems/Petrushina-MS-Thesis/blob/master/slides/Slides2025Petrushina.pdf) | +| Khabutdinov Ildar | Исправление грамматических ошибок в домене низкоресурсных языков | [Grabovoy A. V.](https://andriygav.github.io/) | [Project](https://github.com/intsystems/Khabutdinov-MS-Thesis) | [Thesis](https://github.com/intsystems/Khabutdinov-MS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Khabutdinov-MS-Thesis/blob/master/slides/slides.pdf) | +| Marat Khusainov | Understanding the Plasticity of Neural Networks Employed in GFlowNets | Samsonov S.V. | [Project](https://github.com/intsystems/Khusainov-MS-Thesis/tree/master/) | [Thesis](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Khusainov-MS-Thesis/blob/master/slides/slides.pdf) | #### Bachelor's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -| Zadvornov Egor | Forecasting highly volatile time series of social trends and public interests | [Malkov A.S.](https://scholar.google.ca/citations?user=oDdwPF8AAAAJ&hl=en) | [Project](https://github.com/intsystems/Zadvornov_Egor_paper/tree/master)| [Thesis](https://github.com/intsystems/Zadvornov_Egor_paper/blob/master/paper/main.pdf)|[Slides](https://github.com/intsystems/Zadvornov_Egor_paper/blob/master/slides/Zadvornov_Slides_for_paper_2025.pdf)| -| Firsov Sergey | Neural architecture search with target hardware control | [Bakhteev O.Y.](https://bahleg.site/publications) | [Project](https://github.com/intsystems/Firsov_KOT_DARTS)| [Thesis](https://github.com/intsystems/Firsov_FBNet/blob/master/paper/main_paper.pdf)|[Slides](https://github.com/intsystems/Firsov_FBNet/blob/master/slides/slides.pdf)| -| Ilya Stepanov | Using Synthetic Data Obtained by Generative Neural Networks to Improve the Quality of Detection Models | [Grabovoy A.V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master)| [Thesis](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master/paper/main.pdf)|[Slides](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master/slides/main.pdf)| -| Rebrikov Alexey | Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Rebrikov-BS-Thesis/tree/master)| [Thesis](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/paper/main.pdf)| [Slides](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/slides/main.pdf)| -| Khafizov Fanis | Adaptive Compression in Distributed Optimization | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Khafizov-BS-Thesis)| [Thesis](https://github.com/intsystems/Khafizov-BS-Thesis/blob/master/paper/BachelorThesis_paper.pdf)| [Slides](https://github.com/intsystems/Khafizov-BS-Thesis/blob/master/slides/main.pdf)| -| Rubtsov Denis | High-probability guarantees in stochastic optimization | [Gasnikov A.V.](https://ru.wikipedia.org/wiki/Гасников,_Александр_Владимирович) | [Project](https://github.com/intsystems/Rubtsov-BS-thesis/tree/master)| [Thesis](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/paper/RUBTSOV_DIPLOMA.pdf)| [Slides](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/slides/Rubtsov_bachelor_diploma_slides.pdf)| -| Papay Ivan | Ordinal Classification Using Partially Ordered Feature Sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Papay-BS-Thesis)| [Thesis](https://github.com/intsystems/Papay-BS-Thesis/blob/master/paper/PartialOrders.pdf)| [Slides](https://github.com/intsystems/Papay-BS-Thesis/blob/master/slides/PartialOrders_slides.pdf)| -| Nabiev Muhammadsharif | Predictive multitask model selection using symbolic regression methods | [Bakhteev O.Y.](https://bahleg.site/publications) | [Project](https://github.com/intsystems/Nabiev-BS-Thesis)| [Thesis](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/Nabiev2025IB.pdf)| [Slides](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/Nabiev2025IBSlides.pdf)| -| Eynullayev Altay | Forecasting models in riemannian phase space | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Eynullayev-BS-Thesis)| [Thesis](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/paper/paper.pdf)| [Slides](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/slides/slides_diplom.pdf)| -| Sobolevsky Fedor | Application of large language models for hierarchical summarization of scientific texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Project](https://github.com/intsystems/Sobolevsky-BS-Thesis) | [Thesis](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/paper/Sobolevsky2025BSThesis.pdf) | [Slides](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/slides/2025_Sobolevsky_BS_Thesis_Slides.pdf) | -| Kasiuk Vadim | Application of the compression operator in federative learning | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Kasiuk-BS-Thesis) | [Thesis](https://github.com/intsystems/Kasiuk-BS-Thesis/blob/main/docs/Kasiuk2024CompressionForDistributedOptimization.pdf) | [Slides](https://github.com/intsystems/Kasiuk-BS-Thesis/blob/main/slides/Kasiuk2024CompressionForDistributedOptimization_slides_pdf__Copy_%20(1).pdf) | -| Meshkov Vladislav | ConvNets Landscape Convergence: Hessian-Based Analysis of Matricized Networks | [Grabovoy A.V.](https://andriygav.github.io) |[Project](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/tree/master) |[Thesis](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/diploma/main_diploma.pdf) | [Slides](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/diploma/slides_diploma.pdf) | -| Линич Анастасия | Оценка частичных доказательств в Lean 4 на основе анализа матриц внимания большой языковой модели | Баранников С.А. |[Project](https://github.com/khilling/diploma) |[Thesis](https://github.com/khilling/diploma/blob/main/%D0%92%D0%9A%D0%A0.pdf) | [Slides](https://github.com/khilling/diploma/blob/main/%D0%9F%D1%80%D0%B5%D0%B7%D0%B5%D0%BD%D1%82%D0%B0%D1%86%D0%B8%D1%8F_%D0%92%D0%9A%D0%A0.pdf) | -| Karpeev Gleb | Generative models for forecasting time series sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/2024-Project-152/tree/master)| [Thesis](https://github.com/intsystems/2024-Project-152/blob/master/paper/thesis%20latest.pdf)| [Slides](https://github.com/intsystems/2024-Project-152/blob/master/slides/slides%20latest.pdf)| +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :-------------------- | :------------------------------------------------------------------------------------------------------ | :------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------ | +| Zadvornov Egor | Forecasting highly volatile time series of social trends and public interests | [Malkov A.S.](https://scholar.google.ca/citations?user=oDdwPF8AAAAJ&hl=en) | [Project](https://github.com/intsystems/Zadvornov_Egor_paper/tree/master) | [Thesis](https://github.com/intsystems/Zadvornov_Egor_paper/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Zadvornov_Egor_paper/blob/master/slides/Zadvornov_Slides_for_paper_2025.pdf) | +| Firsov Sergey | Neural architecture search with target hardware control | [Bakhteev O.Y.](https://bahleg.site/publications) | [Project](https://github.com/intsystems/Firsov_KOT_DARTS) | [Thesis](https://github.com/intsystems/Firsov_FBNet/blob/master/paper/main_paper.pdf) | [Slides](https://github.com/intsystems/Firsov_FBNet/blob/master/slides/slides.pdf) | +| Ilya Stepanov | Using Synthetic Data Obtained by Generative Neural Networks to Improve the Quality of Detection Models | [Grabovoy A.V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master) | [Thesis](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Stepanov-BS-Thesis/tree/master/slides/main.pdf) | +| Rebrikov Alexey | Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Rebrikov-BS-Thesis/tree/master) | [Thesis](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Rebrikov-BS-Thesis/blob/master/slides/main.pdf) | +| Khafizov Fanis | Adaptive Compression in Distributed Optimization | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Khafizov-BS-Thesis) | [Thesis](https://github.com/intsystems/Khafizov-BS-Thesis/blob/master/paper/BachelorThesis_paper.pdf) | [Slides](https://github.com/intsystems/Khafizov-BS-Thesis/blob/master/slides/main.pdf) | +| Rubtsov Denis | High-probability guarantees in stochastic optimization | [Gasnikov A.V.](https://ru.wikipedia.org/wiki/Гасников,_Александр_Владимирович) | [Project](https://github.com/intsystems/Rubtsov-BS-thesis/tree/master) | [Thesis](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/paper/RUBTSOV_DIPLOMA.pdf) | [Slides](https://github.com/intsystems/Rubtsov-BS-thesis/blob/master/slides/Rubtsov_bachelor_diploma_slides.pdf) | +| Papay Ivan | Ordinal Classification Using Partially Ordered Feature Sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Papay-BS-Thesis) | [Thesis](https://github.com/intsystems/Papay-BS-Thesis/blob/master/paper/PartialOrders.pdf) | [Slides](https://github.com/intsystems/Papay-BS-Thesis/blob/master/slides/PartialOrders_slides.pdf) | +| Nabiev Muhammadsharif | Predictive multitask model selection using symbolic regression methods | [Bakhteev O.Y.](https://bahleg.site/publications) | [Project](https://github.com/intsystems/Nabiev-BS-Thesis) | [Thesis](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/Nabiev2025IB.pdf) | [Slides](https://github.com/intsystems/Nabiev-BS-Thesis/blob/master/paper/Nabiev2025IBSlides.pdf) | +| Eynullayev Altay | Forecasting models in riemannian phase space | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Eynullayev-BS-Thesis) | [Thesis](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/paper/paper.pdf) | [Slides](https://github.com/intsystems/Eynullayev-BS-Thesis/blob/master/slides/slides_diplom.pdf) | +| Sobolevsky Fedor | Application of large language models for hierarchical summarization of scientific texts | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Project](https://github.com/intsystems/Sobolevsky-BS-Thesis) | [Thesis](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/paper/Sobolevsky2025BSThesis.pdf) | [Slides](https://github.com/intsystems/Sobolevsky-BS-Thesis/blob/main/slides/2025_Sobolevsky_BS_Thesis_Slides.pdf) | +| Kasiuk Vadim | Application of the compression operator in federative learning | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Kasiuk-BS-Thesis) | [Thesis](https://github.com/intsystems/Kasiuk-BS-Thesis/blob/main/docs/Kasiuk2024CompressionForDistributedOptimization.pdf) | [Slides]() | +| Meshkov Vladislav | ConvNets Landscape Convergence: Hessian-Based Analysis of Matricized Networks | [Grabovoy A.V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/tree/master) | [Thesis](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/diploma/main_diploma.pdf) | [Slides](https://github.com/intsystems/Hessian-Based-Analysis-of-Matricized-Networks/blob/master/diploma/slides_diploma.pdf) | +| Линич Анастасия | Оценка частичных доказательств в Lean 4 на основе анализа матриц внимания большой языковой модели | Баранников С.А. | [Project](https://github.com/khilling/diploma) | [Thesis](https://github.com/khilling/diploma/blob/main/%D0%92%D0%9A%D0%A0.pdf) | [Slides](https://github.com/khilling/diploma/blob/main/%D0%9F%D1%80%D0%B5%D0%B7%D0%B5%D0%BD%D1%82%D0%B0%D1%86%D0%B8%D1%8F_%D0%92%D0%9A%D0%A0.pdf) | +| Karpeev Gleb | Generative models for forecasting time series sets | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/2024-Project-152/tree/master) | [Thesis](https://github.com/intsystems/2024-Project-152/blob/master/paper/thesis%20latest.pdf) | [Slides](https://github.com/intsystems/2024-Project-152/blob/master/slides/slides%20latest.pdf) | ### 2024 - #### Master's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -|Maria Kovaleva|Addition of external information for enhancement of local embeddings for event sequences data models|[Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) |[Project](https://github.com/MarKovka20/transactions_gen_models/tree/main)|[Thesis](https://github.com/MarKovka20/transactions_gen_models/blob/main/thesis.pdf)|[Slides](https://github.com/MarKovka20/transactions_gen_models/blob/main/Kovaleva_Maria_thesis_presentation_en.pdf)| -| Alexander Tolmachev | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Project](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main) | [Thesis](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Thesis.pdf) | [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Thesis_defense_presentation_Tolmachev.pdf) | -| Emil Alkin | Expressive Power of Tensor-Train Networks With Equal TT-cores | [Ivan Oseledets](https://faculty.skoltech.ru/people/ivanoseledets) | [Project](https://github.com/AlkinEmil/MasterThesisPublic) | [Thesis](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/Thesis.pdf) | [Slides](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/PredefenceSlides.pdf) | -| Klypa Roman | Generative modeling for protein structures | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/) |[Project](https://github.com/ljk-rk/MolBindDif) | [Thesis](https://github.com/romanklypa/intsystems_thesis/blob/main/masters_diploma_Klypa.pdf) | [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/masters_slides_Klypa.pdf)| -| Ksenofontov Gregory | Adversarial Schrödinger bridges on domain translation problem | [Isachenko R.V.]() | [Project](https://github.com/gregkseno/masters-thesis) | [Paper](https://github.com/gregkseno/masters-thesis/blob/master/diploma/KsenofontovMastersThesis2024.pdf) | [Slides](https://github.com/gregkseno/masters-thesis/blob/master/slides/KsenofonotvMastersThesisSlides2024.pdf)| -| Barabanshchikova Polina | Tverberg type theorems| [Polyanskii A.A.](http://polyanskii.com/) |[Project](https://github.com/pollinab/MasterThesis) | [Paper](https://github.com/pollinab/MasterThesis/blob/main/Master_thesis.pdf) | [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_thesis.pdf)| -| Yakovlev Konstantin | Generalized Greedy Gradient-Based Hyperparameter Optimization | [Bakhteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=en) |[Project](https://github.com/Konstantin-Iakovlev/HyperOpt) | [Paper](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/paper/MsThesisYakovlev.pdf) | [Slides](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/slides/main.pdf)| +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :---------------------- | :--------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :-------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------- | +| Maria Kovaleva | Addition of external information for enhancement of local embeddings for event sequences data models | [Zaytsev A. A.](https://faculty.skoltech.ru/people/alexeizaitsev) | [Project](https://github.com/MarKovka20/transactions_gen_models/tree/main) | [Thesis](https://github.com/MarKovka20/transactions_gen_models/blob/main/thesis.pdf) | [Slides](https://github.com/MarKovka20/transactions_gen_models/blob/main/Kovaleva_Maria_thesis_presentation_en.pdf) | +| Alexander Tolmachev | Information Bottleneck Analysis of Deep Neural Networks | [Alexey Frolov](https://faculty.skoltech.ru/people/alexeyfrolov) | [Project](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main) | [Thesis](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Thesis.pdf) | [Slides](https://github.com/Alexandr-Tolmachev/Master-Thesis-public/blob/main/Thesis_defense_presentation_Tolmachev.pdf) | +| Emil Alkin | Expressive Power of Tensor-Train Networks With Equal TT-cores | [Ivan Oseledets](https://faculty.skoltech.ru/people/ivanoseledets) | [Project](https://github.com/AlkinEmil/MasterThesisPublic) | [Thesis](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/Thesis.pdf) | [Slides](https://github.com/AlkinEmil/MasterThesisPublic/blob/main/PredefenceSlides.pdf) | +| Klypa Roman | Generative modeling for protein structures | [Grudinin S.V.](https://team.inria.fr/nano-d/team-members/sergei-grudinin/) | [Project](https://github.com/ljk-rk/MolBindDif) | [Thesis](https://github.com/romanklypa/intsystems_thesis/blob/main/masters_diploma_Klypa.pdf) | [Slides](https://github.com/romanklypa/intsystems_thesis/blob/main/masters_slides_Klypa.pdf) | +| Ksenofontov Gregory | Adversarial Schrödinger bridges on domain translation problem | [Isachenko R.V.]() | [Project](https://github.com/gregkseno/masters-thesis) | [Paper](https://github.com/gregkseno/masters-thesis/blob/master/diploma/KsenofontovMastersThesis2024.pdf) | [Slides](https://github.com/gregkseno/masters-thesis/blob/master/slides/KsenofonotvMastersThesisSlides2024.pdf) | +| Barabanshchikova Polina | Tverberg type theorems | [Polyanskii A.A.](http://polyanskii.com/) | [Project](https://github.com/pollinab/MasterThesis) | [Paper](https://github.com/pollinab/MasterThesis/blob/main/Master_thesis.pdf) | [Slides](https://github.com/pollinab/MasterThesis/blob/main/Slides_thesis.pdf) | +| Yakovlev Konstantin | Generalized Greedy Gradient-Based Hyperparameter Optimization | [Bakhteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=en) | [Project](https://github.com/Konstantin-Iakovlev/HyperOpt) | [Paper](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/paper/MsThesisYakovlev.pdf) | [Slides](https://github.com/Konstantin-Iakovlev/HyperOpt/blob/main/slides/main.pdf) | #### Bachelor's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -| Nikita Kiselev | Bayesian Sample Size Estimation | [Grabovoy A.V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Kiselev-BS-Thesis) | [Thesis](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/slides/main.pdf) | -| Daniil Dorin | Spatial-temporal characteristics in the time series decoding | [Grabovoy A.V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Dorin-BS-Thesis) | [Thesis](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/paper/paper.pdf) | [Slides](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/slides/slides.pdf) | -| Andrey Veprikov | Mathematical model of the hidden feedback loop effect in machine learning systems | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Project](https://github.com/intsystems/Veprikov-BS-Thesis) | [Thesis](https://github.com/intsystems/Veprikov-BS-Thesis/blob/master/paper/Диплом_Веприков.pdf) | [Slides](https://github.com/intsystems/Veprikov-BS-Thesis/blob/master/slides/Презентация_Диплом_Веприков.pdf) | -| Maria Nikitina | Analysis of distribution bias in contrastive learning | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/Nikitina-BS-Thesis) | [Thesis](https://github.com/intsystems/Nikitina-BS-Thesis/blob/master/paper/NikitinaPaper.pdf) | [Slides](https://github.com/intsystems/Nikitina-BS-Thesis/blob/master/slides/NikitinaSlides.pdf) | -| Anastasia Voznyuk | Detection of machine-generated fragments based on text style change analysis | [Grabovoy A. V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Voznyuk-BS-Thesis) | [Thesis](https://github.com/intsystems/Voznyuk-BS-Thesis/blob/master/paper/thesis/Voznyuk_BS_Thesis.pdf) | [Slides](https://github.com/intsystems/Voznyuk-BS-Thesis/blob/master/slides/ThesisDefenseSlides.pdf) | -| Anna Remizova | Reducing the dimension of the space of the trainable parameters in the domain adaptation problem | [Grabovoy A. V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/code) | [Thesis](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/paper) | [Slides](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/slides) | -|Okhotnikov Nikita | Interconnected latent representations for outfit generation task | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/Okhotnikov-BS-Thesis) | [Thesis](https://github.com/intsystems/Okhotnikov-BS-Thesis/blob/main/paper/main.pdf) | [Slides](https://github.com/intsystems/Okhotnikov-BS-Thesis/blob/main/slides/slides_Okhotnikov.pdf) | -|Terentyev Alexander | Classification of trajectories of dynamic systems using physically-informed neural networks | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/code) | [Thesis](https://github.com/intsystems/Terentev-BS-Thesis/blob/master/paper/TerentyevBSThesis.pdf)| [Slides](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/slides/Slides.pdf) | -| Ignashin Igor | Bayesian distillation of transformer-based models | [Grabovoy A. V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Ignashin-BS-Thesis) | [Thesis](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/paper/Paper_Bayesian_distilation_Ignashin_BS_Thesis%20(9).pdf) | [Slides](https://github.com/intsystems/Ignashin-BS-Thesis/blob/master/slides/Presentation_Bayesian_distilation_Ignashin_BS_Thesis%20(19).pdf) | -| Ilgam Latypov | An effective method of scalarization and search for a competitive solution without iterative calculations for Lipschitz functions | [Dorn Y.V.](https://scholar.google.ru/citations?user=ByIc-l8AAAAJ&hl=ru) | [Project](https://github.com/intsystems/NIR_LatypovIM/tree/main) | [Thesis](https://github.com/intsystems/NIR_LatypovIM/blob/main/paper/Latypov_diploma.pdf) | [Slides](https://github.com/intsystems/NIR_LatypovIM/blob/main/paper/Latypov_presentation.pdf) | -| Kirill Semkin |Tensor decomposition and forecast for multidimensional time series | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/tssa_method/tree/master) | [Thesis](https://github.com/intsystems/tssa_method/blob/master/doc/Tensor_SSA_Semkin.pdf) | [Slides](https://github.com/intsystems/tssa_method/blob/master/doc/slides/Tensor_SSA_Semkin_Slides.pdf) | -| Matvei Kreinin | On methods with preconditioning and weight decaying | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Kreinin-BS-Thesis/tree/master) | [Thesis](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/docs/Kreinin_BS_Thesis.pdf) | [Slides](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/slides/slides.pdf) | -| Petr Babkin | Differentiable algorithm for searching ensembles of deep learning models with diversity control | [Bakhteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=en) | [Project](https://github.com/intsystems/2023-Project-120/tree/master) | [Thesis](https://github.com/intsystems/2023-Project-120/blob/master/paper/EdgeNES_diploma-5.pdf) | [Slides](https://github.com/intsystems/2023-Project-120/blob/master/slides/EdgeNES_slides.pdf) | -| Bogdanov Alexander | Gradient approximations using a zero-order oracle and memorization technique | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Bogdanov-BS-Thesis) | [Thesis](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/paper/BachelorThesis_paper.pdf) | [Slides](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/slides/BachelorThesis_slides.pdf) | -| Oleinik Mikhail | Knowledge distillation in deep neural networks using model structure alignment methods | [Bakhteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=en) | [Project](https://github.com/intsystems/Oleinik-BS-Thesis) | [Thesis](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/paper/Oleinik_thesis.pdf) | [Slides](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/slides/main.pdf) | - +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :------------------ | :-------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------- | :--------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------- | +| Nikita Kiselev | Bayesian Sample Size Estimation | [Grabovoy A.V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Kiselev-BS-Thesis) | [Thesis](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/paper/main.pdf) | [Slides](https://github.com/intsystems/Kiselev-BS-Thesis/blob/master/slides/main.pdf) | +| Daniil Dorin | Spatial-temporal characteristics in the time series decoding | [Grabovoy A.V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Dorin-BS-Thesis) | [Thesis](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/paper/paper.pdf) | [Slides](https://github.com/intsystems/Dorin-BS-Thesis/blob/master/slides/slides.pdf) | +| Andrey Veprikov | Mathematical model of the hidden feedback loop effect in machine learning systems | [Khritankov A.S.](https://www.hse.ru/org/persons/501143261) | [Project](https://github.com/intsystems/Veprikov-BS-Thesis) | [Thesis](https://github.com/intsystems/Veprikov-BS-Thesis/blob/master/paper/Диплом_Веприков.pdf) | [Slides](https://github.com/intsystems/Veprikov-BS-Thesis/blob/master/slides/Презентация_Диплом_Веприков.pdf) | +| Maria Nikitina | Analysis of distribution bias in contrastive learning | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/Nikitina-BS-Thesis) | [Thesis](https://github.com/intsystems/Nikitina-BS-Thesis/blob/master/paper/NikitinaPaper.pdf) | [Slides](https://github.com/intsystems/Nikitina-BS-Thesis/blob/master/slides/NikitinaSlides.pdf) | +| Anastasia Voznyuk | Detection of machine-generated fragments based on text style change analysis | [Grabovoy A. V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Voznyuk-BS-Thesis) | [Thesis](https://github.com/intsystems/Voznyuk-BS-Thesis/blob/master/paper/thesis/Voznyuk_BS_Thesis.pdf) | [Slides](https://github.com/intsystems/Voznyuk-BS-Thesis/blob/master/slides/ThesisDefenseSlides.pdf) | +| Anna Remizova | Reducing the dimension of the space of the trainable parameters in the domain adaptation problem | [Grabovoy A. V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/code) | [Thesis](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/paper) | [Slides](https://github.com/intsystems/Remizova-BS-Thesis/tree/master/slides) | +| Okhotnikov Nikita | Interconnected latent representations for outfit generation task | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/Okhotnikov-BS-Thesis) | [Thesis](https://github.com/intsystems/Okhotnikov-BS-Thesis/blob/main/paper/main.pdf) | [Slides](https://github.com/intsystems/Okhotnikov-BS-Thesis/blob/main/slides/slides_Okhotnikov.pdf) | +| Terentyev Alexander | Classification of trajectories of dynamic systems using physically-informed neural networks | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/code) | [Thesis](https://github.com/intsystems/Terentev-BS-Thesis/blob/master/paper/TerentyevBSThesis.pdf) | [Slides](https://github.com/intsystems/Terentev-BS-Thesis/tree/master/slides/Slides.pdf) | +| Ignashin Igor | Bayesian distillation of transformer-based models | [Grabovoy A. V.](https://andriygav.github.io) | [Project](https://github.com/intsystems/Ignashin-BS-Thesis) | [Thesis]() | [Slides]() | +| Ilgam Latypov | An effective method of scalarization and search for a competitive solution without iterative calculations for Lipschitz functions | [Dorn Y.V.](https://scholar.google.ru/citations?user=ByIc-l8AAAAJ&hl=ru) | [Project](https://github.com/intsystems/NIR_LatypovIM/tree/main) | [Thesis](https://github.com/intsystems/NIR_LatypovIM/blob/main/paper/Latypov_diploma.pdf) | [Slides](https://github.com/intsystems/NIR_LatypovIM/blob/main/paper/Latypov_presentation.pdf) | +| Kirill Semkin | Tensor decomposition and forecast for multidimensional time series | [Isachenko R.V.](https://intsystems.github.io/ru/people/isachenko_rv/index.html) | [Project](https://github.com/intsystems/tssa_method/tree/master) | [Thesis](https://github.com/intsystems/tssa_method/blob/master/doc/Tensor_SSA_Semkin.pdf) | [Slides](https://github.com/intsystems/tssa_method/blob/master/doc/slides/Tensor_SSA_Semkin_Slides.pdf) | +| Matvei Kreinin | On methods with preconditioning and weight decaying | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Kreinin-BS-Thesis/tree/master) | [Thesis](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/docs/Kreinin_BS_Thesis.pdf) | [Slides](https://github.com/intsystems/Kreinin-BS-Thesis/blob/master/slides/slides.pdf) | +| Petr Babkin | Differentiable algorithm for searching ensembles of deep learning models with diversity control | [Bakhteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=en) | [Project](https://github.com/intsystems/2023-Project-120/tree/master) | [Thesis](https://github.com/intsystems/2023-Project-120/blob/master/paper/EdgeNES_diploma-5.pdf) | [Slides](https://github.com/intsystems/2023-Project-120/blob/master/slides/EdgeNES_slides.pdf) | +| Bogdanov Alexander | Gradient approximations using a zero-order oracle and memorization technique | [Beznosikov A.N.](https://anbeznosikov.github.io/) | [Project](https://github.com/intsystems/Bogdanov-BS-Thesis) | [Thesis](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/paper/BachelorThesis_paper.pdf) | [Slides](https://github.com/intsystems/Bogdanov-BS-Thesis/blob/main/slides/BachelorThesis_slides.pdf) | +| Oleinik Mikhail | Knowledge distillation in deep neural networks using model structure alignment methods | [Bakhteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=en) | [Project](https://github.com/intsystems/Oleinik-BS-Thesis) | [Thesis](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/paper/Oleinik_thesis.pdf) | [Slides](https://github.com/intsystems/Oleinik-BS-Thesis/blob/master/slides/main.pdf) | ### 2023 - -#### PhD's Theses - -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| - - #### Master's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -| Rustem Islamov | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Project](https://github.com/intsystems/Islamov-MS-Thesis) |[Paper](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Paper/Islamov2023MasterThesis.pdf)|[Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf)| -| Olga Grebenkova | Automatic detection of focal cortical dysplasia for sparse data representation | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ) | [Project](https://github.com/intsystems/Grebenkova-MS-Thesis) | [Thesis](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/MSc_Thesis_PreDefence_Grebenkova.pdf) | [Slides](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/Slides_predef.pdf) | -| Anton Bishuk | Controlled Graph Generation | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Project](https://github.com/intsystems/Bishuk-MS-Thesis) | [Thesis](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/paper/Bishuk-MS-thesis-defense.pdf) | [Slides](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/slides/Bishuk-MS-slides-defense.pdf) | -| Nadezhda Alsahanova | Selection of tensor representations for multiview forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/NadezhdaAlsahanova/MSThesis) | [Thesis](https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Doc/MS_Thesis_rus.pdf) | [Slides](https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Slides/Presentation_rus.pdf) | -| Robert Safiullin | Multimodel representation of dynamic systems | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Safiullin-MS-Thesis) | [Thesis]( https://github.com/intsystems/Safiullin-MS-Thesis/blob/master/paper/Master_s_Thesis.pdf) | [Slides](https://github.com/intsystems/Safiullin-MS-Thesis/blob/master/slides/SafiullinMS_slides.pdf) | -| Shokorov Viacheslav | Deep ensemble boosting | [Vetrov D.P.](https://scholar.google.ca/citations?user=7HU0UoUAAAAJ) | [Project](https://github.com/vshokorov/margin_based_ensembles_boosting) | [Thesis](https://github.com/vshokorov/margin_based_ensembles_boosting/blob/main/reports/Shokorov2023MasterThesis.pdf) | [Slides](https://github.com/vshokorov/margin_based_ensembles_boosting/blob/main/reports/Shokorov2023MasterSlides.pdf) | -| Filatov Andrei | Text Interfaces for Event Sequences | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Filatov-MS-Thesis) | [Thesis](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/paper/FilatovMScThesis.pdf) | [Slides](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/slides/MScThesisPresentation.pdf) | -| Viktor Pankratov | Probabilistic Topic Modeling for Unbalanced Text Collections | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Project](https://github.com/intsystems/Pankratov-MS-Thesis) | [Thesis](https://github.com/intsystems/Pankratov-MS-Thesis/blob/main/paper/Pankratov_MS_Thesis.pdf) | [Slides](https://github.com/intsystems/Pankratov-MS-Thesis/blob/main/slides/Pankratov_MS_Thesis.pdf) | +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :------------------ | :--------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------- | +| Rustem Islamov | Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation | [Strijov V.V.](http://www.ccas.ru/strijov/), [Richtarik P.](https://richtarik.org/) | [Project](https://github.com/intsystems/Islamov-MS-Thesis) | [Paper](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Paper/Islamov2023MasterThesis.pdf) | [Slides](https://github.com/intsystems/Islamov-MS-Thesis/blob/main/Presentation/Islamov2023PresentationMS.pdf) | +| Olga Grebenkova | Automatic detection of focal cortical dysplasia for sparse data representation | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ) | [Project](https://github.com/intsystems/Grebenkova-MS-Thesis) | [Thesis](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/MSc_Thesis_PreDefence_Grebenkova.pdf) | [Slides](https://github.com/intsystems/Grebenkova-MS-Thesis/blob/main/Slides_predef.pdf) | +| Anton Bishuk | Controlled Graph Generation | [Zukhba A.V.](https://mipt.ru/education/post-graduate/archive_main/fupm_d212.156.05/Candidates/Zukhba_Anastasiya_Viktorovna#.YboMr31Bw-Q) | [Project](https://github.com/intsystems/Bishuk-MS-Thesis) | [Thesis](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/paper/Bishuk-MS-thesis-defense.pdf) | [Slides](https://github.com/intsystems/Bishuk-MS-Thesis/blob/main/slides/Bishuk-MS-slides-defense.pdf) | +| Nadezhda Alsahanova | Selection of tensor representations for multiview forecasting | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/NadezhdaAlsahanova/MSThesis) | [Thesis](https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Doc/MS_Thesis_rus.pdf) | [Slides](https://github.com/NadezhdaAlsahanova/MSThesis/blob/main/Slides/Presentation_rus.pdf) | +| Robert Safiullin | Multimodel representation of dynamic systems | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Safiullin-MS-Thesis) | [Thesis](https://github.com/intsystems/Safiullin-MS-Thesis/blob/master/paper/Master_s_Thesis.pdf) | [Slides](https://github.com/intsystems/Safiullin-MS-Thesis/blob/master/slides/SafiullinMS_slides.pdf) | +| Shokorov Viacheslav | Deep ensemble boosting | [Vetrov D.P.](https://scholar.google.ca/citations?user=7HU0UoUAAAAJ) | [Project](https://github.com/vshokorov/margin_based_ensembles_boosting) | [Thesis](https://github.com/vshokorov/margin_based_ensembles_boosting/blob/main/reports/Shokorov2023MasterThesis.pdf) | [Slides](https://github.com/vshokorov/margin_based_ensembles_boosting/blob/main/reports/Shokorov2023MasterSlides.pdf) | +| Filatov Andrei | Text Interfaces for Event Sequences | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Filatov-MS-Thesis) | [Thesis](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/paper/FilatovMScThesis.pdf) | [Slides](https://github.com/intsystems/Filatov-MS-Thesis/blob/master/slides/MScThesisPresentation.pdf) | +| Viktor Pankratov | Probabilistic Topic Modeling for Unbalanced Text Collections | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Project](https://github.com/intsystems/Pankratov-MS-Thesis) | [Thesis](https://github.com/intsystems/Pankratov-MS-Thesis/blob/main/paper/Pankratov_MS_Thesis.pdf) | [Slides](https://github.com/intsystems/Pankratov-MS-Thesis/blob/main/slides/Pankratov_MS_Thesis.pdf) | #### Bachelor's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -| Eduard Vladimirov | State space models in ECoG signal classification problem | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Vladimirov-BS-Thesis) |[Paper](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/paper/VladimirovTSModels.pdf)|[Slides](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/slides/VladimirovTSModels.pdf)| -| Georgiy Zharov | Searching for links between fragments of manipulations with named entities in texts | Vorontsov K.V. | [Project](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main) |[Paper](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/paper)|[Slides](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/slides)| -| Alexander Molozhavenko |Riemannian optimization on the manifold of fixed rank tensor trains with the orthogonality condition | Gasnikov A.V. | [Project](https://github.com/intsystems/Molozhavenko-BS-Thesis/tree/master) |[Paper](https://github.com/intsystems/Molozhavenko-BS-Thesis/blob/master/paper/Diploma_pdf/Bachelor_Thesis.pdf)|[Slides](https://github.com/intsystems/Molozhavenko-BS-Thesis/blob/master/slides/Diploma_slides/Diploma_Presentation.pdf)| -|Ivan Lukyanenko|Manipulation detection in news| Vorontsov. K.V. | [Project](https://github.com/intsystems/Lukyanenko-BS-Thesis) | [Paper](https://github.com/intsystems/Lukyanenko-BS-Thesis/blob/master/Lukyanenko-Thesis-Final.pdf) | [Slides](https://github.com/intsystems/Lukyanenko-BS-Thesis/blob/master/slides/Bachelor_Thesis_Slides%20(4).pdf)| -| Antyshev Tikhon |Gradient Sliding for Composite Saddle Point Problems | Gasnikov A.V. | [Project](https://github.com/intsystems/Antyshev-BS-Thesis/tree/master) |[Paper](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/paper/Antyshev_Sliding_Thesis.pdf)|[Slides](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/slides/slides.pdf)| -| Kornilov Nikita |Gradient Free Methods for Non-Smooth Convex Stochastic Optimization with Heavy Tails on Convex Compact | Gasnikov A.V. | [Project](https://github.com/intsystems/Kornilov-BS-Thesis) |[Paper](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/paper/Kornilov_Diploma_full.pdf)|[Slides](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/slides/InfZero_Grad_Pres_RUS.pdf)| +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :--------------------- | :----------------------------------------------------------------------------------------------------- | :------------------------------------------ | :-------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------ | +| Eduard Vladimirov | State space models in ECoG signal classification problem | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/intsystems/Vladimirov-BS-Thesis) | [Paper](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/paper/VladimirovTSModels.pdf) | [Slides](https://github.com/intsystems/Vladimirov-BS-Thesis/blob/master/slides/VladimirovTSModels.pdf) | +| Georgiy Zharov | Searching for links between fragments of manipulations with named entities in texts | Vorontsov K.V. | [Project](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main) | [Paper](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/paper) | [Slides](https://github.com/Egor-s-gor/Zharov-BS-Thesis/tree/main/slides) | +| Alexander Molozhavenko | Riemannian optimization on the manifold of fixed rank tensor trains with the orthogonality condition | Gasnikov A.V. | [Project](https://github.com/intsystems/Molozhavenko-BS-Thesis/tree/master) | [Paper](https://github.com/intsystems/Molozhavenko-BS-Thesis/blob/master/paper/Diploma_pdf/Bachelor_Thesis.pdf) | [Slides](https://github.com/intsystems/Molozhavenko-BS-Thesis/blob/master/slides/Diploma_slides/Diploma_Presentation.pdf) | +| Ivan Lukyanenko | Manipulation detection in news | Vorontsov. K.V. | [Project](https://github.com/intsystems/Lukyanenko-BS-Thesis) | [Paper](https://github.com/intsystems/Lukyanenko-BS-Thesis/blob/master/Lukyanenko-Thesis-Final.pdf) | [Slides]() | +| Antyshev Tikhon | Gradient Sliding for Composite Saddle Point Problems | Gasnikov A.V. | [Project](https://github.com/intsystems/Antyshev-BS-Thesis/tree/master) | [Paper](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/paper/Antyshev_Sliding_Thesis.pdf) | [Slides](https://github.com/intsystems/Antyshev-BS-Thesis/blob/master/slides/slides.pdf) | +| Kornilov Nikita | Gradient Free Methods for Non-Smooth Convex Stochastic Optimization with Heavy Tails on Convex Compact | Gasnikov A.V. | [Project](https://github.com/intsystems/Kornilov-BS-Thesis) | [Paper](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/paper/Kornilov_Diploma_full.pdf) | [Slides](https://github.com/intsystems/Kornilov-BS-Thesis/blob/main/slides/InfZero_Grad_Pres_RUS.pdf) | ### 2022 +#### PhD Theses -#### PhD's Theses - -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -| Andrey Grabovoy | Bayesian Distilation | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/andriygav/PhDThesis) | [Thesis](https://github.com/andriygav/PhDThesis/raw/master/thesis/Grabovoy2021PhDThesis.pdf)| [Slides](https://github.com/andriygav/PhDThesis/raw/master/slides/Grabovoy2021PhDSlides.pdf)| - +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :-------------- | :------------------- | :------------------------------------------ | :------------------------------------------------ | :------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------- | +| Andrey Grabovoy | Bayesian Distilation | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/andriygav/PhDThesis) | [Thesis](https://github.com/andriygav/PhDThesis/raw/master/thesis/Grabovoy2021PhDThesis.pdf) | [Slides](https://github.com/andriygav/PhDThesis/raw/master/slides/Grabovoy2021PhDSlides.pdf) | #### Master's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -| Alexey Grigorev | Regularization of neural layer via construction of frame in parameter space | [Gneushev A.N.](https://scholar.google.com/citations?hl=en&user=sjlY2q8AAAAJ) | [Project](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/tree/master) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/Grigorev2022Thesis.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/Grigorev2022Slides.pdf) -| Natalia Varenik | Building a connectivity map of functional groups in the problem of decoding brain signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/tree/master) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/paper/Varenik2022master_thesis_final.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/paper/Varenik2022master_slides-4.pdf)| -| Pavel Severilov | Choosing the optimal model in the problem of modeling dynamics of a physical system by neural networks | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/severilov/master-thesis/tree/main/code) | [Thesis](https://github.com/severilov/master-thesis/blob/main/doc/Severilov2022MasterThesis_rus.pdf) | [Slides](https://github.com/severilov/master-thesis/blob/main/pres/Severilov2022MasterThesisPres.pdf)| -| Panchenko Sviatoslav | Bilinearity of geometric product for the task of signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/tree/main/code) | [Thesis](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/paper/Panchenko2022MasterThesis.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/slides/Panchenko2022MasterPresentation.pdf)| -| Alexey Grishanov | Application of Reinforcement Learning for recommendation system personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Project](https://github.com/Intelligent-Systems-Phystech/Grishanov-MS-Thesis/tree/master) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Grishanov-MS-Thesis/blob/master/Grishanov2022Thesis.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Grishanov-MS-Thesis/blob/master/Grishanov2022presentation.pdf)| -| Petr Mokrov | Wasserstein gradient flows: modeling and applications | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ) | [Project](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/tree/master/paper) | [Slides](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/tree/master/slides) | -| Tikhonov Denis | Forecasting models selection for quasi-periodic time series | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Denis-Tihonov/Tikhonov-Ms-Thesis) | [Thesis](https://github.com/Denis-Tihonov/Tikhonov-Ms-Thesis/blob/main/Thesis/Tikhonov_MS_Thesis.pdf) | [Slides](https://github.com/Denis-Tihonov/Tikhonov-Ms-Thesis/blob/main/Slides/Tikhonov_2022_MS_Presentation.pdf)| -| Kolesov Alexander | Adversarial training approach for a neural network in Transfer Learning problem | [Bahteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=ru) | [Project](https://github.com/justkolesov/Optimal-Transfer-Learning)| [Thesis](https://github.com/justkolesov/Optimal-Transfer-Learning/blob/main/Thesis_Kolesov.pdf) | [Slides](https://github.com/justkolesov/Optimal-Transfer-Learning/blob/main/Kolesov_presentation.pdf) | - +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :------------------- | :----------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------ | +| Alexey Grigorev | Regularization of neural layer via construction of frame in parameter space | [Gneushev A.N.](https://scholar.google.com/citations?hl=en&user=sjlY2q8AAAAJ) | [Project](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/tree/master) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/Grigorev2022Thesis.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/blob/master/Grigorev2022Slides.pdf) | +| Natalia Varenik | Building a connectivity map of functional groups in the problem of decoding brain signals | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/Grigorev-MS-Thesis/tree/master) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/paper/Varenik2022master_thesis_final.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Varenik-MS-Thesis/raw/master/paper/Varenik2022master_slides-4.pdf) | +| Pavel Severilov | Choosing the optimal model in the problem of modeling dynamics of a physical system by neural networks | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/severilov/master-thesis/tree/main/code) | [Thesis](https://github.com/severilov/master-thesis/blob/main/doc/Severilov2022MasterThesis_rus.pdf) | [Slides](https://github.com/severilov/master-thesis/blob/main/pres/Severilov2022MasterThesisPres.pdf) | +| Panchenko Sviatoslav | Bilinearity of geometric product for the task of signal decoding | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/tree/main/code) | [Thesis](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/paper/Panchenko2022MasterThesis.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/GeometricAlgebra/blob/main/slides/Panchenko2022MasterPresentation.pdf) | +| Alexey Grishanov | Application of Reinforcement Learning for recommendation system personalization | [Vorontsov K.V.](http://www.machinelearning.ru/wiki/index.php?title=User:Vokov) | [Project](https://github.com/Intelligent-Systems-Phystech/Grishanov-MS-Thesis/tree/master) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Grishanov-MS-Thesis/blob/master/Grishanov2022Thesis.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Grishanov-MS-Thesis/blob/master/Grishanov2022presentation.pdf) | +| Petr Mokrov | Wasserstein gradient flows: modeling and applications | [Burnaev E.V.](https://scholar.google.ru/citations?user=pCRdcOwAAAAJ) | [Project](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/tree/master/paper) | [Slides](https://github.com/Intelligent-Systems-Phystech/Mokrov_Ms_Thesis/tree/master/slides) | +| Tikhonov Denis | Forecasting models selection for quasi-periodic time series | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Denis-Tihonov/Tikhonov-Ms-Thesis) | [Thesis](https://github.com/Denis-Tihonov/Tikhonov-Ms-Thesis/blob/main/Thesis/Tikhonov_MS_Thesis.pdf) | [Slides](https://github.com/Denis-Tihonov/Tikhonov-Ms-Thesis/blob/main/Slides/Tikhonov_2022_MS_Presentation.pdf) | +| Kolesov Alexander | Adversarial training approach for a neural network in Transfer Learning problem | [Bahteev O.Y.](https://scholar.google.ru/citations?user=7eWNuFkAAAAJ&hl=ru) | [Project](https://github.com/justkolesov/Optimal-Transfer-Learning) | [Thesis](https://github.com/justkolesov/Optimal-Transfer-Learning/blob/main/Thesis_Kolesov.pdf) | [Slides](https://github.com/justkolesov/Optimal-Transfer-Learning/blob/main/Kolesov_presentation.pdf) | #### Bachelor's Theses -| Student | Thesis topic | Scientific adviser | Link to Project | Link to Paper | Link to Slides | -|:---:|:---:|:---:|:---:|:---:|:---:| -| Kurdyukova Antonina | Dimensionality reduction in the phase space in canonical correlation analysis|[Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/raw/master/docs/Kurdyukova2022BSThesis.pdf)| [Slides](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/raw/master/slides/Kurdyukova2022Slides.pdf)| -| Gorpinich Mariya | Metaparameter optimization in knowledge distillation|[Bakhteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Oleg_Bakhteev) | [Project](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/Gorpinich2021DistillingKnowledge.pdf)| [Slides](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/slides/Gorpinich2021DistillingKnowledge_slides.pdf)| -| Gorсhakov Vyacheslav | Importance Sampling Approach to Chance-Constrained DC Optimal Power Flow |[Maximov Y.V.]() | [Project](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/Gorchakov_BS_Thesis_text.pdf)| [Slides](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/BS_thesis_slides.pdf)| -| Pilkevich Anton | Optimization of the criterion given by the neural network model in the text detoxification task|[Strijov V.V.](http://www.ccas.ru/strijov/)| [Project](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/main.pdf)| [Slides](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/pres.pdf)| -| Khristolybov Maxim | Model parameter space for phase trajectory approximation|[Strijov V.V.](http://www.ccas.ru/strijov/)| [Project](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/blob/main/paper/Khristolyubov_Bacalavr_Thesis%20(24).pdf)| [Slides](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/blob/main/slides/BS_slides_.pdf)| +| Student | Topic | Advisor | Link to Project | Link to Paper | Link to Slides | +| :------------------- | :---------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------ | +| Kurdyukova Antonina | Dimensionality reduction in the phase space in canonical correlation analysis | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/raw/master/docs/Kurdyukova2022BSThesis.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Kurdyukova-BS-Thesis/raw/master/slides/Kurdyukova2022Slides.pdf) | +| Gorpinich Mariya | Metaparameter optimization in knowledge distillation | [Bakhteev O.Yu.](http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Oleg_Bakhteev) | [Project](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/Gorpinich2021DistillingKnowledge.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Gorpinich-BS-Thesis/raw/master/paper/slides/Gorpinich2021DistillingKnowledge_slides.pdf) | +| Gorсhakov Vyacheslav | Importance Sampling Approach to Chance-Constrained DC Optimal Power Flow | [Maximov Y.V.]() | [Project](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/Gorchakov_BS_Thesis_text.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Gorchakov-BS-thesis/blob/master/docs/BS_thesis_slides.pdf) | +| Pilkevich Anton | Optimization of the criterion given by the neural network model in the text detoxification task | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis) | [Thesis](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/main.pdf) | [Slides](https://github.com/Intelligent-Systems-Phystech/Pilkevich-BS-Thesis/blob/master/docs/pres.pdf) | +| Khristolybov Maxim | Model parameter space for phase trajectory approximation | [Strijov V.V.](http://www.ccas.ru/strijov/) | [Project](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis) | [Thesis]() | [Slides](https://github.com/Intelligent-Systems-Phystech/Khristolyubov-BS-Thesis/blob/main/slides/BS_slides_.pdf) | diff --git a/_i18n/ru.yml b/_i18n/ru.yml index 9950c7bc..71f88c47 100755 --- a/_i18n/ru.yml +++ b/_i18n/ru.yml @@ -9,19 +9,23 @@ site: nav: names: - home: главная - about: о кафедре - lecturers: преподаватели - courses: курсы - materials: материалы - admission: поступающим - nir: отчеты нир - scholarship: стипендии - conferences: список конференций - thesis: дипломы - education: расписание - seminars: семинары - paper_guidelines: как писать научные работы + home: Главная + education: Расписание + lecturers: Преподаватели + courses: Курсы + admission: Поступающим + materials: Материалы + nir: Отчеты НИР + thesis: Дипломы + seminars: Семинары + scholarship: Стипендии + paper_guidelines: Как писать научные работы + templates: Шаблоны + conferences: Список конференций + + toc: + title: Содержание + toggle: Свернуть или развернуть содержание global: course: @@ -29,139 +33,89 @@ site: bachelor: Бакалавриат master: Магистратура deprecated: Больше не преподаются + draft: В разработке people: roles: hotd: Основатели кафедры dos: Доктора наук phd: Кандидаты наук - gs: Аспиранты + pgs: Аспиранты + gs: Студенты template: ПРИМЕР -peoples: - name: - grabovoy_av: Грабовой Андрей Валериевич - aduenko_aa: Адуенко Александр Александрович - bakhteev_oy: Бахтеев Олег Юрьевич - khrilchenko_ky: Хрыльченко Кирилл Ярославович - isachenko_rv: Исаченко Роман Владимирович - khritankov_as: Хританков Антон Сергеевич - kropotov_da: Кропотов Дмитрий Александрович - meysuradze_ai: Майсурадзе Арчил Ивериевич - mestetskiy_lm: Местецкий Леонид Моисеевич - popov_as: Попов Артем Сергеевич - potanin_ms: Потанин Марк Станиславович - strijov_vv: Стрижов Вадим Викторович - vorontsov_kv: Воронцов Константин Вячеславович - torshin_iy: Торшин Иван Юрьевич - rudakov_kv: Рудаков Константин Владимирович - zhuravlyov_yv: Журавлев Юрий Иванович - apishev_ma: Апишев Мурат Азаматович - gneushev_an: Гнеушев Александр Николаевич - dulin_sk: Дулин Сергей Константинович - khoroshevsky_vf: Хорошевский Владимир Федорович - mohonko_ez: Мохонько Елена Захаровна - tsurkov_vi: Цурков Владимир Иванович - matveev_ia: Матвеев Иван Алексеевич - chekhovich_yv: Чехович Юрий Викторович - grebenkova_os: Гребенькова Ольга Сергеевна - filatov_av: Филатов Андрей Викторович - samokhina_am: Самохина Алина Максимовна - severilov_pa: Северилов Павел Андреевич - bishuk_ay: Бишук Антон Юрьевич - grishanov_av: Гришанов Алексей Владимирович - volodkevich_aa: Володкевич Анна Алексеевна - beznosikov_an: Безносиков Александр Николаевич - mokrov_pv: Мокров Петр Владимирович - tikhonov_dm: Тихонов Денис Максимович - yakovlev_kd: Яковлев Константин Дмитриевич - - title: - grabovoy_av: Грабовой Андрей Валериевич - aduenko_aa: Адуенко Александр Александрович - bakhteev_oy: Бахтеев Олег Юрьевич - khrilchenko_ky: Хрыльченко Кирилл Ярославович - isachenko_rv: Исаченко Роман Владимирович - khritankov_as: Хританков Антон Сергеевич - kropotov_da: Кропотов Дмитрий Александрович - meysuradze_ai: Майсурадзе Арчил Ивериевич - mestetskiy_lm: Местецкий Леонид Моисеевич - popov_as: Попов Артем Сергеевич - potanin_ms: Потанин Марк Станиславович - strijov_vv: Стрижов Вадим Викторович - vorontsov_kv: Воронцов Константин Вячеславович - torshin_iy: Торшин Иван Юрьевич - rudakov_kv: Рудаков Константин Владимирович - zhuravlyov_yv: Журавлев Юрий Иванович - apishev_ma: Апишев Мурат Азаматович - gneushev_an: Гнеушев Александр Николаевич - dulin_sk: Дулин Сергей Константинович - khoroshevsky_vf: Хорошевский Владимир Федорович - mohonko_ez: Мохонько Елена Захаровна - tsurkov_vi: Цурков Владимир Иванович - matveev_ia: Матвеев Иван Алексеевич - chekhovich_yv: Чехович Юрий Викторович - grebenkova_os: Гребенькова Ольга Сергеевна - filatov_av: Филатов Андрей Викторович - samokhina_am: Самохина Алина Максимовна - severilov_pa: Северилов Павел Андреевич - bishuk_ay: Бишук Антон Юрьевич - grishanov_av: Гришанов Алексей Владимирович - volodkevich_aa: Володкевич Анна Алексеевна - beznosikov_an: Безносиков Александр Николаевич - mokrov_pv: Мокров Петр Владимирович - tikhonov_dm: Тихонов Денис Максимович - yakovlev_kd: Яковлев Константин Дмитриевич +people: + grabovoy_av: Грабовой Андрей Валериевич + aduenko_aa: Адуенко Александр Александрович + bakhteev_oy: Бахтеев Олег Юрьевич + khrilchenko_ky: Хрыльченко Кирилл Ярославович + isachenko_rv: Исаченко Роман Владимирович + khritankov_as: Хританков Антон Сергеевич + kropotov_da: Кропотов Дмитрий Александрович + meysuradze_ai: Майсурадзе Арчил Ивериевич + mestetskiy_lm: Местецкий Леонид Моисеевич + popov_as: Попов Артем Сергеевич + potanin_ms: Потанин Марк Станиславович + strijov_vv: Стрижов Вадим Викторович + vorontsov_kv: Воронцов Константин Вячеславович + torshin_iy: Торшин Иван Юрьевич + rudakov_kv: Рудаков Константин Владимирович + zhuravlyov_yv: Журавлев Юрий Иванович + apishev_ma: Апишев Мурат Азаматович + gneushev_an: Гнеушев Александр Николаевич + dulin_sk: Дулин Сергей Константинович + khoroshevsky_vf: Хорошевский Владимир Федорович + mohonko_ez: Мохонько Елена Захаровна + tsurkov_vi: Цурков Владимир Иванович + matveev_ia: Матвеев Иван Алексеевич + chekhovich_yv: Чехович Юрий Викторович + grebenkova_os: Гребенькова Ольга Сергеевна + filatov_av: Филатов Андрей Викторович + samokhina_am: Самохина Алина Максимовна + severilov_pa: Северилов Павел Андреевич + bishuk_ay: Бишук Антон Юрьевич + grishanov_av: Гришанов Алексей Владимирович + volodkevich_aa: Володкевич Анна Алексеевна + mokrov_pv: Мокров Петр Владимирович + tikhonov_dm: Тихонов Денис Максимович + yakovlev_kd: Яковлев Константин Дмитриевич + panchenko_sk: Панченко Святослав Константинович + vladimirov_ea: Владимиров Эдуард Анатольевич + dorin_dd: Дорин Даниил Дмитриевич + kiselev_ns: Киселев Никита Сергеевич + firsov_sa: Фирсов Сергей Андреевич + kasyuk_va: Касюк Вадим Александрович + morozov_ma: Морозов Матвей Алексеевич + kreinin_mv: Крейнин Матвей Вадимович + nikitina_ma: Никитина Мария Александровна courses: - name: - automation_scientific_research: Автоматизация научных исследований - bayesian_model_selection: Байесовский выбор моделей - bayesian_multimodeling: Байесовское мультимоделирование - bioinformatics: Биоинформатика - computational_geometry: Алгоритмы вычислительной геометрии - deep_generative_models: Порождающие модели машинного обучения - deep_learning: Методы глубокого обучения - image_processing_recognition: Обработка и распознавание изображений - introduction_machine_learning: Введение в машинное обучение - forecasting_methods: Математические методы прогнозирования - fundamental_ml_theorems: Фундаментальные теоремы машинного обучения - natural_language_processing: Математические методы анализа текстов - networks_text_analysis: Анализ сетей и текстов - neural_architecture_search: Поиск нейросетевых архитектур - probabilistic_topic_models: Вероятностные тематические модели - recommender_systems: Рекомендательные системы - rnd_in_ai: Создание интеллектуальных систем - signal_processing: Обработка сигналов - software_engineering_data_analysis: Программная инженерия для анализа данных - intellectual_data_analysis: Интеллектуальный анализ данных - optimization_methods: Методы оптимизации в машинном обучении - - title: - automation_scientific_research: Автоматизация научных исследований - bayesian_model_selection: Байесовский выбор моделей - bayesian_multimodeling: Байесовское мультимоделирование - bioinformatics: Биоинформатика - computational_geometry: Алгоритмы вычислительной геометрии - deep_generative_models: Порождающие модели машинного обучения - deep_learning: Методы глубокого обучения - forecasting_methods: Математические методы прогнозирования - fundamental_ml_theorems: Фундаментальные теоремы машинного обучения - image_processing_recognition: Обработка и распознавание изображений - introduction_machine_learning: Введение в машинное обучение - networks_text_analysis: Анализ сетей и текстов - neural_architecture_search: Поиск нейросетевых архитектур - natural_language_processing: Математические методы анализа текстов - probabilistic_topic_models: Вероятностные тематические модели - recommender_systems: Рекомендательные системы - rnd_in_ai: Создание интеллектуальных систем - signal_processing: Обработка сигналов и многомерных массивов данных - software_engineering_data_analysis: Программная инженерия для анализа данных - intellectual_data_analysis: Интеллектуальный анализ данных - optimization_methods: Методы оптимизации в машинном обучении - + automation_scientific_research: Автоматизация научных исследований + bayesian_model_selection: Байесовский выбор моделей + bayesian_multimodeling: Байесовское мультимоделирование + bioinformatics: Биоинформатика + computational_geometry: Алгоритмы вычислительной геометрии + deep_generative_models: Порождающие модели машинного обучения + deep_learning: Методы глубокого обучения + image_processing_recognition: Обработка и распознавание изображений + introduction_machine_learning: Введение в машинное обучение + forecasting_methods: Математические методы прогнозирования + fundamental_ml_theorems: Фундаментальные теоремы машинного обучения + natural_language_processing: Математические методы анализа текстов + networks_text_analysis: Анализ сетей и текстов + neural_architecture_search: Поиск нейросетевых архитектур + probabilistic_topic_models: Вероятностные тематические модели + recommender_systems: Рекомендательные системы + rnd_in_ai: Создание интеллектуальных систем + signal_processing: Обработка сигналов + software_engineering_data_analysis: Программная инженерия для анализа данных + intellectual_data_analysis: Интеллектуальный анализ данных + deep_learning_audio: Глубокое обучение для аудио + programming_practicum_python: Практикум по программированию на Python + functional_data_analysis: Функциональный анализ данных + computer_vision: Компьютерное зрение + titles: index: Интеллектуальные системы - about: О кафедре course: Курсы people: Преподаватели materials: Материалы @@ -173,6 +127,7 @@ titles: admission: Поступающим seminars: Научные семинары paper_guidelines: Рекомендации по написанию ВКР и научных работ + templates: Шаблоны course: teachers: Преподаватели @@ -183,6 +138,6 @@ profile: teaches: Преподает metatags: - lecturer: Преподаватель Кафедры интеллектуальных систем МФТИ - bachelor_course: Курс бакалаврской программы Кафедры интеллектуальных систем МФТИ - master_course: Курс магистерской программы Кафедры интеллектуальных систем МФТИ + lecturer: Преподаватель Кафедры интеллектуальных систем МФТИ + bachelor_course: Курс бакалаврской программы Кафедры интеллектуальных систем МФТИ + master_course: Курс магистерской программы Кафедры интеллектуальных систем МФТИ diff --git a/_i18n/ru/_course/automation_scientific_research.md b/_i18n/ru/_course/automation_scientific_research.md old mode 100755 new mode 100644 index 9e8e68f4..9310bd3d --- a/_i18n/ru/_course/automation_scientific_research.md +++ b/_i18n/ru/_course/automation_scientific_research.md @@ -1,25 +1,26 @@ -### О курсе "Моя первая научная статья" -В рамках этого курса студент готовится к научной работе в области машинного обучения. Он работает в персональной исследовательской группе. Каждая группа состоит из студента, консультанта и эксперта. Цель курса – научиться точно, ясно, красиво излагать свои и чужие идеи. Задача – написать научную статью, которая была бы принята другими исследователями, работающими в нашей области; сделать доклад. +### О курсе -### Страница курса -* Материалы и домашние задания: [m1p.org](https://m1p.org/) -* Страница 2022 года: [Project m1p_2022](https://github.com/Intelligent-Systems-Phystech/m1p_2022) +В рамках этого курса студент готовится к научной работе в области машинного обучения. Он работает в персональной исследовательской группе. Каждая группа состоит из студента, консультанта и эксперта. Цель курса – научиться точно, ясно, красиво излагать свои и чужие идеи. Задача – написать научную статью, которая была бы принята другими исследователями, работающими в нашей области; сделать доклад. ### Тематический план -* Выбор своего проекта. -* Постановка задачи. -* Планирование эксперимента. -* Визуализация данных. -* Теоретическое решение задачи. -* Анализ ошибки. -* Написание статьи. -* Подготовка доклада. + +- Выбор своего проекта. +- Постановка задачи. +- Планирование эксперимента. +- Визуализация данных. +- Теоретическое решение задачи. +- Анализ ошибки. +- Написание статьи. +- Подготовка доклада. ### Самостоятельная работа + Личный проект в области прикладной математики или машинного обучения, выполняемый под руководством консультанта. Результат – научная статья, код, доклад. ### Оценивание + Каждая неделя состоит из нескольких заданий. Выполнение задания дает один балл согласно расписанию. ### Требуемые знания + Знание алгебры и математического анализа в объеме двух курсов ФУПМ МФТИ. diff --git a/_i18n/ru/_course/bayesian_model_selection.md b/_i18n/ru/_course/bayesian_model_selection.md index 9c3fefe7..20ea1b4a 100755 --- a/_i18n/ru/_course/bayesian_model_selection.md +++ b/_i18n/ru/_course/bayesian_model_selection.md @@ -1,27 +1,32 @@ ### О курсе + Курс посвящен изучению основ байесовских методов машинного обучения, построения байесовских моделей данных и вывода в них. Рассматриваются оптимальные байесовские прогнозы, а также методы их построения. Освещаются способы учета нелинейностей и неоднородностей в данных, пропусков в данных, а также эволюции оптимальной модели во времени. ### Темы -* Введение: Напоминание понятий из теории вероятностей и статистики. -* Множественное тестирование гипотез и выбор априорного распределения. -* Наивный байесовский классификатор, его обобщения и оптимальный прогноз. Экспоненциальное семейство распределений. -* Байесовская линейная регрессия. Обоснованность (evidence). -* Байесовская логистическая регрессия и отбор признаков. -* EM-алгоритм и вариационный EM-алгоритм. -* Гауссовские процессы и эволюция моделей во времени. -* Построение адекватных мультимоделей. -* Методы Монте-Карло по схеме марковских цепей. -* Гамильтоновы методы Монте-Карло по схеме марковских цепей. -* Байесовская оптимизация. + +- Введение: Напоминание понятий из теории вероятностей и статистики. +- Множественное тестирование гипотез и выбор априорного распределения. +- Наивный байесовский классификатор, его обобщения и оптимальный прогноз. Экспоненциальное семейство распределений. +- Байесовская линейная регрессия. Обоснованность (evidence). +- Байесовская логистическая регрессия и отбор признаков. +- EM-алгоритм и вариационный EM-алгоритм. +- Гауссовские процессы и эволюция моделей во времени. +- Построение адекватных мультимоделей. +- Методы Монте-Карло по схеме марковских цепей. +- Гамильтоновы методы Монте-Карло по схеме марковских цепей. +- Байесовская оптимизация. ### Самостоятельная работа + 4 теоретических задания (выполняются индивидуально), 1 практическое задание и 1 соревнование (выполняются по командам), 2 теста. Письменный и устный экзамен (последний можно заменить докладом на тему по выбору). -### Оценивание +### Оценивание + Каждое теоретическое задание дает максимум 50 или 100 баллов, практическое и соревнование — до 150. Баллы автора лучшей работы удваиваются (дополнительные баллы). Устный и письменный экзамен добавляют до 250 баллов. Общая оценка рассчитывается шкалированием к максимально возможной без учета дополнительных баллов. ### Требуемые знания + Знание теории вероятностей, основ машинного обучения, линейной алгебры и методов оптимизации. diff --git a/_i18n/ru/_course/bayesian_multimodeling.md b/_i18n/ru/_course/bayesian_multimodeling.md index e6092df8..cfbd0969 100755 --- a/_i18n/ru/_course/bayesian_multimodeling.md +++ b/_i18n/ru/_course/bayesian_multimodeling.md @@ -1,14 +1,19 @@ ### О курсе + Данный курс посвящен проблеме выбора моделей в задачах машинного обучения и анализа данных. В рамках курса рассматривается байесовский подход к задаче выбора моделей, его теоретические и практические аспекты. Рассматриваются особенности различных подходов к решению задач выбора, агрегации и композиции как для моделей специального вида, так и для общего вида моделей. ### Тематический план + В курсе рассматриваются особенности выбора моделей для разных типов моделей: от линейных до смесей экспертов, построенных на моделях глубокого обучения. Рассматриваются различные подходы к выбору моделей и настройке гиперпараметров, включая градиентные методы, методы sequential model based optimization, методы на основе гиперсетей и суперсетей. ### Самостоятельная работа -4 практических работы, 2 доклада по желанию каждый семестр. Каждую неделю также проводится анкетирование по итогам занятия. + +1 проектная работа и 1 доклад каждый семестр. Каждую неделю также проводится анкетирование по итогам занятия. ### Оценивание -Оценка складывается из практических заданий, докладов и ответов на анкету. + +Оценка складывается из баллов за проект, доклад и ответы на анкету. ### Требуемые знания + Статистика, линейная алгебра, машинное обучение, глубокое обучение, элементы байесовского вывода. diff --git a/_i18n/ru/_course/bioinformatics.md b/_i18n/ru/_course/bioinformatics.md index d2ed0fe4..9f0c19d1 100755 --- a/_i18n/ru/_course/bioinformatics.md +++ b/_i18n/ru/_course/bioinformatics.md @@ -1,27 +1,32 @@ ### О курсе + В курсе лекций рассматриваются уникальные особенности биологических данных, приводящие к оригинальным постановкам задач распознавания и классификации. Следует отметить, что практически для всех рассматриваемых в курсе задач пока еще не было предложено точных и математически обоснованных решений. В этом смысле курс представляет обширное поле деятельности для самостоятельной научной работы студентов. Формулируется система задач распознавания, отражающая структуру биологических систем и дающая основу для построения проблемно-ориентированных теорий. Рассматриваются основы формализма, разрабатываемого для решения задач биоинформатики и других плохо-формализованных задач из области перспективных биомедицинских исследований и сентимент-анализа. Данный формализм основан на теории универсальных и локальных ограничений в рамках алгебраического подхода к распознаванию. Уделяется внимание биомедицинским приложениям результатов интеллектуального анализа биологических данных. ### Тематический план -* От клеточной биологии к задачам распознавания -* Биологические данные, объекты и подходы к формализации задач. -* Задачи 1D→1D: сравнение символьных последовательностей. -* Задачи 1Dднк. Задачи 1Dднк и 3Dднк. Задачи 1Dрнк, 2Dрнк, 3Dрнк. -* Рентгено-структурный анализ и ЯМР белков, задачи 3Dб→3Dб и 3Dб→2Dб. -* Разработка проблемно-ориентированной теории на примере задачи распознавания вторичной структуры. -* Задачи 1Dб→1Dб. -* Задачи 1Dб→Ф и 3D→Ф и задача аннотации генома. -* Анализ и синтез биологических сетей. -* Молекулярная фармакология и хемоинформатика. -* Биомедицинские и генетические исследования. -* Анализ текстов, использование баз данных. -* Био-логика и алгоритмы. + +- От клеточной биологии к задачам распознавания +- Биологические данные, объекты и подходы к формализации задач. +- Задачи 1D→1D: сравнение символьных последовательностей. +- Задачи 1Dднк. Задачи 1Dднк и 3Dднк. Задачи 1Dрнк, 2Dрнк, 3Dрнк. +- Рентгено-структурный анализ и ЯМР белков, задачи 3Dб→3Dб и 3Dб→2Dб. +- Разработка проблемно-ориентированной теории на примере задачи распознавания вторичной структуры. +- Задачи 1Dб→1Dб. +- Задачи 1Dб→Ф и 3D→Ф и задача аннотации генома. +- Анализ и синтез биологических сетей. +- Молекулярная фармакология и хемоинформатика. +- Биомедицинские и генетические исследования. +- Анализ текстов, использование баз данных. +- Био-логика и алгоритмы. ### Самостоятельная работа -В ходе лекций будут объявляться практические задания. Студенты могут сами формулировать темы исследовательских задач. После выбора задачи, обсуждаются требования к работе. + +В ходе лекций будут объявляться практические задания. Студенты могут сами формулировать темы исследовательских задач. После выбора задачи обсуждаются требования к работе. ### Оценивание + До начала устного экзамена (отчет-презентация) необходимо сдать отчет об исследовательской работе (3-5 стр), проведенной по выбранной задаче. ### Требуемые знания + Основыв машинного обучения. diff --git a/_i18n/ru/_course/computational_geometry.md b/_i18n/ru/_course/computational_geometry.md index 81e188c7..38aba256 100755 --- a/_i18n/ru/_course/computational_geometry.md +++ b/_i18n/ru/_course/computational_geometry.md @@ -1,19 +1,24 @@ ### О курсе + В курсе рассматриваются основные алгоритмы вычислительной геометрии. ### Тематический план -* Геометрический поиск. -* Построение выпуклых оболочек. -* Определение пересечений объектов. -* Диаграммы Вороного и триангуляции Делоне. -* Близость геометрических объектов. -* Срединные оси и скелеты. + +- Геометрический поиск. +- Построение выпуклых оболочек. +- Определение пересечений объектов. +- Диаграммы Вороного и триангуляции Делоне. +- Близость геометрических объектов. +- Срединные оси и скелеты. ### Самостоятельная работа + В курсе предполагается решение нескольких лабораторных работ. ### Оценивание + Оценка выставляется по результатам лабораторных работ и устного экзамена. ### Требуемые знания + Основы машинного обучения, структуры данных и алгоритмы. diff --git a/_i18n/ru/_course/computer_vision.md b/_i18n/ru/_course/computer_vision.md new file mode 100755 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/ru/_course/computer_vision.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/ru/_course/deep_generative_models.md b/_i18n/ru/_course/deep_generative_models.md index 18471a8a..51b964f1 100755 --- a/_i18n/ru/_course/deep_generative_models.md +++ b/_i18n/ru/_course/deep_generative_models.md @@ -1,29 +1,34 @@ ### О курсе + Курс посвящен современным генеративным моделям машинного обучения. Особое внимание уделяется свойствам различных классов генеративных моделей, их взаимосвязям, теоретическим предпосылкам и методам оценки качества. Цель курса - познакомить студента с широко используемыми передовыми методами построения порождающих моделей. ### Тематический план -1. Введение в генеративное моделирование. Постановка задачи. Задача минимизации дивергенций. Авторегрессионное моделирование. -2. Авторегрессионные модели (WaveNet, PixelCNN). Основы байесовского вывода. Модели скрытых переменных. Вариационная нижняя оценка (ELBO). -3. EM-алгоритм, амортизированный вывод. Градиенты ELBO, репараметризация. Вариационный автокодировщик (VAE).  -4. Недостатки VAE. Коллапс апостериорного распределения VAE. Техники ослабления декодера. Выборка по значимости для ELBO. Якобиан и теорема о замене переменных. -5. Модели нормализующих потоков. Прямая и обратная KL дивергенции. Линейные потоки (Glow). -6. Авторегрессионные потоки (гауссовский и обраный гауссовский поток). Слой связи (RealNVP). Связь нормализующих потоков и VAE.  -7. Дискретные данные, непрерывная модель. Дискретизация модели (PixelCNN++). Равномерная и вариационная деквантизации (Flow++). Теорема об операции над ELBO. Оптимальное априорное распределение в VAE. Потоки в априорном распределении VAE. -8. Потоки в априорном и апостериорном распределении VAE. Неявные генеративные модели без оценки правдоподобия. Модель генеративных состязательных сетей (GAN). Теорема об оптимальности GAN. -9. Проблемы обучения GAN моделей (затухающие градиенты, коллапс мод). KL дивергенция vs JS дивергенция. VAE с неявным энкодером. Топологические особенности обучения GAN моделей. Расстояние Вассерштейна. Дуальность Канторовича-Рубинштейна. GAN Вассерштейна (WGAN). -10. Модель WGAN с градиентным штрафом. Модель WGAN со спектральной нормализацией. Вариационная минимизация f-дивергенций. Оценивание качества неявных моделей. -11. Оценивание качества неявных моделей (Inception score, FID, Precision-Recall, truncation trick). VAE с дискретным скрытым пространством. -12. Векторная квантизация, сквозной градиент (VQ-VAE). Гумбель-софтмакс трюк (DALL-E). Нейронные обыкновенные дифференциальные уравнения. Метод сопряженных функций. -13. Непрерывные во времени нормализационные потоки (FFJORD). Несмещенная оценка следа матрицы. Основы стохастических дифференциальных уравнений. Уравнение Колмогорова-Фоккера-Планка и динамика Ланжевена. Методы оценивания score функции. -14. Модели оценки score функции (NCSM). Гауссовский диффузионый процесс. Диффузионная генеративная модель (DDPM). + +1. Введение в генеративное моделирование. Постановка задачи. Задача минимизации дивергенций. Авторегрессионное моделирование (PixelCNN). +2. Модели нормализующих потоков (NF). Линейные потоки (Glow). Авторегрессионные потоки (гауссовский и обраный гауссовский поток). Слой связи (RealNVP). +3. Прямая и обратная KL дивергенции. Модели скрытых переменных. Вариационная нижняя оценка (ELBO). EM-алгоритм. +4. Амортизированный вывод. Градиенты ELBO, репараметризация. Вариационный автокодировщик (VAE). Связь нормализующих потоков и VAE. VAE с дискретным скрытым пространством. +5. Векторная квантизация, сквозной градиент (VQ-VAE). Гумбель-софтмакс трюк (DALL-E). Теорема об операции над ELBO. Оптимальное априорное распределение в VAE. Потоки в априорном распределении VAE. +6. Неявные генеративные модели без оценки правдоподобия. Модель генеративных состязательных сетей (GAN). Теорема об оптимальности GAN. Расстояние Вассерштейна. +7. GAN Вассерштейна (WGAN). Вариационная минимизация f-дивергенций. Оценивание качества неявных моделей (Inception score, FID, Precision-Recall, truncation trick). +8. Динамика Ланжевена. Методы оценивания score функции. Модели оценки score функции (NCSM). Гауссовский диффузионый процесс. +9. Denoising score matching для диффузии. Обратный гауссовский диффузионный процесс. Гауссовская диффузионная модель как VAE. ELBO для DDPM. +10. Denoising diffusion probabilistic model (DDPM): репараметризация и обзор. Denoising diffusion как score-based генеративная модель. Model guidance: classifier guidance, classifier-free guidance. +11. Нормализующие потоки непрерывного времени и neural ODE. Уравнение непрерывности для log-likelihood NF. FFJORD и оценка следа Хатчинсона. Adjoint метод для NF непрерывного времени. +12. Основы SDE. Уравнение Колмогорова-Фоккера-Планка. Probability flow ODE. Обратное SDE. Variance Preserving и Variance Exploding SDE. +13. Score-based генеративные модели через SDE. Flow matching. Conditional flow matching. Конические гауссовские пути. +14. Линейная интерполяция. Связь с диффузией и score matching. Модели скрытого пространства. ### Cамостоятельная работа + 6 домашних работ, каждая содержит как теоретические задания, так и практические. ### Оценивание -Каждая домашняя работа дает 13 баллов + экзамен на 26 баллов. Финальная оценка: (количество баллов / 8) - 2. + +Каждая домашняя работа дает 15 баллов + экзамен на 30 баллов. Финальная оценка: min(floor(#баллов/10), 10). ### Требуемые знания -Статистика, машинное обучение, глубокое обучение, элементы байесовского вывода. + +Теория вероятностей, статистика, машинное обучение, основы глубокого обучения, python, pytorch, элементы байесовского вывода. diff --git a/_i18n/ru/_course/deep_learning.md b/_i18n/ru/_course/deep_learning.md index 8bb20d6b..9cbc129b 100755 --- a/_i18n/ru/_course/deep_learning.md +++ b/_i18n/ru/_course/deep_learning.md @@ -1,25 +1,34 @@ ### О курсе -Обзорный курс по основным нейросетевым моделям и их применению к различным задачам обработки изображений, текста, звука. + +Курс предоставляет всесторонний обзор современных методов глубокого обучения, от фундаментальных концепций до продвинутых тем. ### Тематический план -* Сети прямого распространения. Матрично-векторное дифференцирование. Автоматическое дифференцирование. -* Методы оптимизации нейронных сетей. Регуляризация DropOut. Библиотека pytorch. -* Инициализация нейронных сетей. Виды нормализации, свёрточные нейронные сети, реализация свёрточных сетей на pytorch. -* Рекуррентные нейронные сети. Решение задачи машинного перевода. Механизм внимания. Модель Transformer. -* Локализация и детекция объектов на изображении. -* Семантическая сегментация изображений. Задача Instance/Panoptic segmentation. -* Обучение с подкреплением. Марковский процесс принятия решений. Уравнения Беллмана. -* Алгоритмы Policy iteration, Value iteration. Q-обучение. Модель DQN. -* Алгоритмы Reinforce, A2C. Многорукие бандиты. -* Генеративные модели. Модель вариационного автокодировщика. -* Авторегрессионные модели PixelCNN, PixelRNN.Методы репараметризации. -* Генеративно-состязательные сети и их модификации. Метрики качества изображений + +1. Многослойный персептрон, обратное распространение ошибки +2. Оптимизация, регуляризация +3. Инициализация, нормализация, сверточные нейронные сети +4. Введение в обработку естественного языка, векторные представления слов +5. RNN, LSTM, Attention, Transformer +6. Классификация, детекция объектов +7. Сегментация +8. Многорукие бандиты, уравнения Беллмана, методы Монте-Карло, обучение с подкреплением, Q-обучение +9. Планирование и двойное обучение, улучшение имеющейся стратегии, градиент по стратегиям +10. Авто-регрессия, VAE, GAN +11. Диффузионные модели, Flow Matching +12. Большие языковые модели, дообучение, LoRA, RAG, агенты +13. Мультимодальные модели, CLIP, Qwen-VL +14. Квантизация, прунинг, дистилляция, KV-Cache, Flash Attention ### Самостоятельная работа -Всего в семестре предполагается 5 практических заданий. Каждое задание оценивается из 10-ти баллов. Все задания можно сдать спустя неделю после мягкого дедлайна со штрафом 0.3 балла в день. Экзамен оценивается из 10-ти баллов. + +6 домашних работ по практической реализации моделей глубокого обучения. ### Оценивание -0.7 * баллы за семестр + 0.3 * баллы за экзамен. + +6 домашних работ дают 70 баллов + экзамен 30 баллов. Финальный балл: `min(round(#points/10), 10)`. ### Требуемые знания -Машинное обучение, статистика, методы оптимизации. + +- Теория вероятностей и статистика +- Машинное обучение +- Python diff --git a/_i18n/ru/_course/deep_learning_audio.md b/_i18n/ru/_course/deep_learning_audio.md new file mode 100755 index 00000000..af9112ca --- /dev/null +++ b/_i18n/ru/_course/deep_learning_audio.md @@ -0,0 +1,40 @@ +### О курсе + +Курс посвящен современным подходам глубокого обучения для обработки и анализа аудио. Особое внимание уделяется основам цифровой обработки сигналов, системам автоматического распознавания речи, синтезу речи и методам нейронной генерации аудио. Цель курса — познакомить студентов с передовыми техниками машинного обучения в области аудио и их практическими применениями. + +### Тематический план + +1. **Цифровая обработка сигналов**: Основы аудио, спектрограммы, STFT и классические методы предобработки аудио. +2. **Автоматическое распознавание речи I**: Word Error Rate (WER), Connectionist Temporal Classification (CTC), Listen-Attend-Spell (LAS) и алгоритмы beam search. +3. **Автоматическое распознавание речи II**: RNN-Transducer (RNN-T), архитектура Conformer, модель Whisper, языковые модели в ASR и Byte-Pair Encoding (BPE). +4. **Key-word Spotting (KWS)**: Детекция ключевых слов, компактные модели и потоковые KWS-системы. +5. **Синтез речи I**: Архитектура Tacotron, модели FastSpeech и механизмы guided attention. +6. **Синтез речи II**: Neural vocoders, включая WaveNet, Parallel WaveGAN и DiffWave для высококачественного синтеза аудио. +7. **Voice Conversion**: Техники трансформации голоса и нейронные подходы к копированию голоса. +8. **Самообучение в аудио**: Wav2Vec, HuBERT и другие self-supervised подходы для обучения представлений аудио. +9. **Неконтролируемое обучение в аудио**: Кластеризация, обучение представлений и методы unsupervised анализа аудио. +10. **Генерация музыки с помощью нейронных сетей**: AI-композиция музыки и техники генерации. + +### Лекции и семинары + +Курс включает теоретические лекции и практические семинары с упражнениями по программированию. Рассматриваемые темы: + +- **Лекции**: Фундаментальные концепции, архитектуры моделей и теоретические основы +- **Семинары**: Практическая реализация с использованием PyTorch, предобработка аудио, обучение и оценка моделей + +### Cамостоятельная работа + +4 домашних задания, охватывающих практические аспекты глубокого обучения в сфере аудио: + +1. **Классификация и предобработка аудио**: Фундаментальная обработка аудио и задачи классификации +2. **ASR с CTC**: Реализация Connectionist Temporal Classification для распознавания речи +3. **ASR с RNN-T**: Продвинутое распознавание речи с использованием архитектуры RNN-Transducer +4. **Синтез речи**: Построение систем text-to-speech на основе FastPitch + +### Оценивание + +Каждое домашнее задание дает 2 балла + итоговый тест на 2 балла. Максимальный балл: 4×2 + 2 = **10 баллов**. + +### Требуемые знания + +Основы цифровой обработки сигналов, фундаментальные знания машинного обучения, глубокое обучение с PyTorch и базовое понимание моделирования последовательностей. diff --git a/_i18n/ru/_course/forecasting_methods.md b/_i18n/ru/_course/forecasting_methods.md index 74fdbcf7..419a64c0 100755 --- a/_i18n/ru/_course/forecasting_methods.md +++ b/_i18n/ru/_course/forecasting_methods.md @@ -1,25 +1,27 @@ ### О курсе + Курс построен на примерах задач построения интерфейса мозг-компьютер и прогнозирования пространственно-временных рядов. Методы машинного обучения рассматриваются с точек зрения физики и прикладной математики. Изучаются элементы тензорного представления данных, функционального и геометрического анализа данных. ### Тематический план -* Авторегрессионные модели. -* Исследование зависимостей. -* Тензорные разложения. -* Нейронные дифференциальные уравнения. -* Непрерывное представление времени и потоки. -* Метрические методы и тензоры. -* Спектральные методы. -* Спектральные графовые модели. -* Геометрический анализ данных. + +- Авторегрессионные модели. +- Исследование зависимостей. +- Тензорные разложения. +- Нейронные дифференциальные уравнения. +- Непрерывное представление времени и потоки. +- Метрические методы и тензоры. +- Спектральные методы. +- Спектральные графовые модели. +- Геометрический анализ данных. ### Самостоятельная работа + Две персональных лабораторных работы по анализу данных головного мозга с постановкой задачи и вычислительным экспериментом. Отчет состоит из двухстраничного описания результатов, кода и доклада. -### Оценивание +### Оценивание + Вопросы в течение занятий (3), две лабораторные работы (2+2), экзамен в конце с обсуждением тем и задач (3). ### Требуемые знания -Знание алгебры, математического анализа и общей физики в объеме трех курсов ФУПМ МФТИ. -### Страница курса -[с подробным расписанием и материалами](https://m1p.org/mf) +Знание алгебры, математического анализа и общей физики в объеме трех курсов ФУПМ МФТИ. diff --git a/_i18n/ru/_course/functional_data_analysis.md b/_i18n/ru/_course/functional_data_analysis.md new file mode 100755 index 00000000..15a6fd62 --- /dev/null +++ b/_i18n/ru/_course/functional_data_analysis.md @@ -0,0 +1,131 @@ +**Channels** + +- [The 2025 course seminar](https://t.me/+XyXmEXRlrXB9dZKD) +- [The chat-link FDA group](https://t.me/+XyXmEXRlrXB9dZKD) + +**When** + +- September 4, 11, 18, 25 — **Thursdays** at 10:30 · [m1p.org/go_zoom](https://m1p.org/go_zoom) +- October (most likely) — **Saturdays** at 10:30 + +--- + +## Foundation models for spatial-time series + +Foundation AI models are universal models for a wide set of problems. This project investigates their theoretical properties on **spatial-time series**—data used across sciences to generalize knowledge and make forecasts. Core user-level tasks: _forecasting_ and _generation_ of time series; _analysis_ and _classification_; _change-point detection_; _causal inference_. These models are trained on massive datasets. Our goal is to compare architectures to find an optimal one that solves the above for a broad range of spatial time series. + +## Functional data analysis + +We assume continuous time and study state-space changes $\frac{d\mathbf{x}}{dt}$ via neural ODEs/SDEs. We analyze multivariate/multidimensional series with tensor representations; model strong cross-correlations in **Riemannian** spaces. Many medical series are periodic; the base model is the pendulum $\frac{d^2 x}{dt^2} = -c\sin x$. We use physics-informed neural networks (PINNs). Practical experiments involve multiple sources; we use canonical correlation analysis with a **latent state space** to align source/target manifolds and enable generation in both. + +## Applications + +Any field with continuous time/space data from multimodal sources: climate, neural interfaces, solid-state physics, electronics, fluid dynamics, and more. We collect both theory and practice. + +--- + +## Fall 2025: Foundation models for time series + +### Topics to discuss + +1. State Space Models, Convolution, SSA, SSM (Spectral Submanifolds) +2. Neural & Controlled ODE, Neural PDE, Geometric Learning +3. Operator Learning, Physics-informed learning, multimodeling +4. Spatio-Temporal Graph Modeling: graph convolution & metric tensors +5. Riemannian models; time series generation +6. AI for science: mathematical modeling principles + +Outside the course: data-driven tensor analysis, differential forms, spinors. + +### State of the Art in 2025 + +In December 2024, a NeurIPS workshop “Foundational models for science” reflected this theme: + +1. Foundation Models for Science: Progress, Opportunities, and Challenges — [URL](https://neurips.cc/virtual/2024/workshop/84714) +2. Foundation Models for the Earth system — [UPL, no paper](https://neurips.cc/virtual/2024/107817) +3. Foundation Methods for foundation models for scientific machine learning — [URL, no paper](https://neurips.cc/virtual/2024/107819) +4. AI-Augmented Climate simulators and emulators — [URL, no paper](https://neurips.cc/virtual/2024/107822) +5. Provable in-context learning of linear systems and linear elliptic PDEs with transformers — [NIPS](https://openreview.net/forum?id=xDstmuxn1D) +6. VSMNO: Solving PDE by Utilizing Spectral Patterns of Different Neural Operators — [NIPS PDF](https://openreview.net/pdf?id=oCT8pYix5e) + +### March 2025 Physics Problem Simulations + +- The Well: a Large-Scale Collection of Diverse Physics Simulations for ML — [arXiv](https://arxiv.org/pdf/2412.00568) · [Code](https://polymathic-ai.org/the_well/data_format/) +- Polymathic: Advancing Science through Multi-Disciplinary AI — [blog](https://polymathic-ai.org/) +- Long Term Memory: The Foundation of AI Self-Evolution — [arXiv](https://arxiv.org/html/2410.15665v1) +- Distilling Free-Form Natural Laws from Experimental Data (2009) — [Science](https://www.science.org/doi/abs/10.1126/science.1165893) · [comment](https://arxiv.org/pdf/1210.7273) · [medium](https://medium.com/@lotussavy/distilling-free-form-natural-laws-from-experimental-data-f55341ae0fa6) +- Deep learning for universal linear embeddings of nonlinear dynamics — [Nature](https://www.nature.com/articles/s41467-018-07210-0) +- A comparison of data-driven approaches to low-dimensional ocean models (2021) — [arXiv](https://arxiv.org/abs/2108.00818) +- Applications of DL to Ocean Data Inference & Subgrid Parameterization (2018) — [preprint](https://eartharxiv.org/repository/view/1142/) +- On energy-aware hybrid models (2024) — [doi](https://doi.org/10.1029/2024MS004306) + +### Spatial-Temporal Graph Modeling + +- Graph WaveNet — [arXiv](https://arxiv.org/abs/1906.00121) +- Diffusion Convolutional Recurrent Neural Network (DCRNN) — [ICLR](https://arxiv.org/abs/1707.01926) +- Time-SSM: Simplifying & Unifying State Space Models — [arXiv](https://arxiv.org/pdf/2405.16312) +- State Space Reconstruction for Multivariate Time Series — [arXiv](https://arxiv.org/abs/0809.2220) +- Longitudinal predictive modeling of tau progression — [NeuroImage 2021](https://www.sciencedirect.com/science/article/pii/S1053811921004031?via%3Dihub) + +--- + +## Work arrangements + +| **Week** | **Date** | **Theme** | **Delivery** | +| -------: | :------- | :------------------------------------------------------------------------------------------------------------------------------------ | :---------------------- | +| 1 | Sep 4 | Preliminary discussion — [pdf](https://github.com/vadim-vic/Foundation-ts/tree/main/doc/Foundation_models_for_time_series_Week_1.pdf) | | +| 2 | Sep 11 | Problem statement — [pdf](https://github.com/vadim-vic/Foundation-ts/tree/main/doc/Foundation_models_for_time_series_Week_2.pdf) | | +| 3 | Sep 18 | Preliminary solution | Group talk & discussion | +| 4 | Sep 25 | Minimum deployment | Group report | +| 5 | Oct 4+ | FDA | Personal talks | +| 13 | Nov 29 | Final discussion | Group talks | + +--- + +## Structure of seminars + +The semester lasts **12 weeks**; six alternate weeks are for homework. + +- **Odd week:** topic intro + homework theme handout. +- **Every week:** essay discussion; collect improvement list. +- **Odd week:** discuss improved essays; integrate into a joint structure. + +### Scoring + +Group activity: cross-ranking with **Kemeny median**. Personal talks contribute to score. + +--- + +## Week 3 — Homework 1 + +1. Form a group. +2. Discuss goals and a solution (\[see the problem statement]). +3. Review solution approaches. +4. Select an LLM-GPT. +5. Run the code; verify it works. + + - Store code in the group repository. + - Store slides/report as well. + +6. Make a 10-minute talk covering: + + - Functionality and architecture of the model. + - Why you selected this model. + - Alternative models considered. + +### Requirements for the text & discussion + +1. Comprehensive explanation of the discussed method/question. +2. Principles only; **no experiments**. +3. \~Two pages. +4. Target reader: 2nd–3rd-year student. +5. One figure is **mandatory**. +6. Brief reference to DL structure is welcome. +7. Talk may be a slide or the text itself. +8. References with DOIs. +9. State how it was generated. +10. Note observed gaps to revisit later. + +### Style remarks for the essays + +Automatic text generation raises the bar for clarity and authorship. Use generative tools to **train persuasion skills**; write for a **thesis defense committee**. diff --git a/_i18n/ru/_course/fundamental_ml_theorems.md b/_i18n/ru/_course/fundamental_ml_theorems.md index 4d0fe0db..9344e7d0 100644 --- a/_i18n/ru/_course/fundamental_ml_theorems.md +++ b/_i18n/ru/_course/fundamental_ml_theorems.md @@ -1,30 +1,33 @@ ### О курсе + Цель курса – научиться строго формулировать задачи машинного обучения и показать роль математического подхода. Навыки, полученные на этом курсе являются основой при написании квалификационных работ бакалавра, магистра и кандидата наук. Курс включает обсуждение аксиоматических систем, теорем и их доказательств, имеющих значение в машинном обучении. Обсуждается их влияние на практические приложения. ### Тематический план -* Теорема Гаусса-Маркова -* Теорема о сингулярном разложении -* Метод главных компонент и разложение Карунена-Лоэва -* Теорема Каруша-Куна-Таккера -* Теоремы Колмогорова и Арнольда, теорема об универсальном аппроксиматоре Цыбенко, теорема о глубоких нейросетях -* Теорема о бесплатных обедах в машинном обучении, Волперт -* Метрические пространства: RKHS Аронжайн, теорема Мерсера -* Теорема схем, Холланда -* Теорема о свертке, теорема Парсеваля -* РАС-learning, сжатие предполагает обучаемость -* Теорема представлений -* Теоремы о бустинге, бутстрепе -* Вариационная аппроксимация -* Теорема о вложениях Такенса -* Теоремы Грина, Стокса, де Рама в геометрическом обучении +- Теорема Гаусса-Маркова +- Теорема о сингулярном разложении +- Метод главных компонент и разложение Карунена-Лоэва +- Теорема Каруша-Куна-Таккера +- Теоремы Колмогорова и Арнольда, теорема об универсальном аппроксиматоре Цыбенко, теорема о глубоких нейросетях +- Теорема о бесплатных обедах в машинном обучении, Волперт +- Метрические пространства: RKHS Аронжайн, теорема Мерсера +- Теорема схем, Холланда +- Теорема о свертке, теорема Парсеваля +- РАС-learning, сжатие предполагает обучаемость +- Теорема представлений +- Теоремы о бустинге, бутстрепе +- Вариационная аппроксимация +- Теорема о вложениях Такенса +- Теоремы Грина, Стокса, де Рама в геометрическом обучении ### Самостоятельная работа -Подготовка и чтение докладов с формулировками, доказательствами и способами применения, значимостью, теорем +Подготовка и чтение докладов с формулировками, доказательствами и способами применения, значимостью, теорем ### Оценивание + Оценивается качество докладов и качество вопросов к докладчику каждого студента ### Требуемые знания + Алгебра и анализ третьего курса МФТИ diff --git a/_i18n/ru/_course/image_processing_recognition.md b/_i18n/ru/_course/image_processing_recognition.md index 1e927a96..29a5aa38 100755 --- a/_i18n/ru/_course/image_processing_recognition.md +++ b/_i18n/ru/_course/image_processing_recognition.md @@ -1,26 +1,31 @@ ### О курсе + Основу курса составляют математические методы распознавания образов, используемые для анализа и классификации изображений в системах компьютерного зрения. Рассматриваются преобразования изображений с целью генерации признаковых описаний. Изучаются методы точечной, пространственной геометрической, алгебраической и межкадровой обработки изображений. Рассматриваются методы генерации признаков на основе разложения изображений по базисным функциям, статистического анализа текстуры изображений, а также анализа формы изображений. -Рассматриваются методы построения метрик для сравнения изображений (сравнение спектральных разложений, наложение и выравнивание образов). А также вопросы применения изученных методов в прикладных задачах компьютерного зрения. Рассматриваются задачи распознавания текстов в изображениях документов, задачи биометрической идентификации личности по текстуре радужной оболочки глаза, по форме ладони, отпечатка пальца, профиля лица. +Рассматриваются методы построения метрик для сравнения изображений (сравнение спектральных разложений, наложение и выравнивание образов). А также вопросы применения изученных методов в прикладных задачах компьютерного зрения. Рассматриваются задачи распознавания текстов в изображениях документов, задачи биометрической идентификации личности по текстуре радужной оболочки глаза, по форме ладони, отпечатка пальца, профиля лица. ### Тематический план -* Предмет и задачи обработки и распознавания цифровых изображений. -* Пространственные методы обработки изображений. -* Геометрические и алгебраические методы обработки изображений. -* Методы межкадровой обработки изображений. -* Анализ изображений на основе разложения по базисным функциям. -* Статистические методы анализа текстур. -* Методы анализа формы изображений. -* Метрики для измерения сходства изображений. -* Распознавание текстов по изображениям документов. -* Биометрическая идентификация на основе распознавания изображений. -* Распознавание динамических сцен. + +- Предмет и задачи обработки и распознавания цифровых изображений. +- Пространственные методы обработки изображений. +- Геометрические и алгебраические методы обработки изображений. +- Методы межкадровой обработки изображений. +- Анализ изображений на основе разложения по базисным функциям. +- Статистические методы анализа текстур. +- Методы анализа формы изображений. +- Метрики для измерения сходства изображений. +- Распознавание текстов по изображениям документов. +- Биометрическая идентификация на основе распознавания изображений. +- Распознавание динамических сцен. ### Самостоятельная работа + Вычислительный практикум по обработке и классификации изображений. ### Оценивание + Оценка выставляется по результатам лабораторных работ и устного экзамена. ### Требуемые знания + Основы машинного обучения, линейная алгебра. diff --git a/_i18n/ru/_course/intellectual_data_analysis.md b/_i18n/ru/_course/intellectual_data_analysis.md index b18d7119..cfeda70a 100755 --- a/_i18n/ru/_course/intellectual_data_analysis.md +++ b/_i18n/ru/_course/intellectual_data_analysis.md @@ -1,11 +1,9 @@ ### О курсе -Курс вводит студентов в полный цикл создания моделей машинного обучения для исследовательских целей. -Основные этапы семестра: анализ прикладной проблемы и постановка задачи, построение модели, выполнение вычислительного эксперимента, анализ ошибки. -Результатом работы группы студентов является библиотека моделей для фиксированной прикладной задачи или класса задач. -[Страница курса](https://github.com/intsystems/ida) +Курс вводит студентов в полный цикл создания моделей машинного обучения для исследовательских целей. +Основные этапы семестра: анализ прикладной проблемы и постановка задачи, построение модели, выполнение вычислительного эксперимента, анализ ошибки. +Результатом работы группы студентов является библиотека моделей для фиксированной прикладной задачи или класса задач. ### Самостоятельная работа -Оценивается: квалификация студента и его личный вклад в проект. - +Оценивается: квалификация студента и его личный вклад в проект. diff --git a/_i18n/ru/_course/introduction_machine_learning.md b/_i18n/ru/_course/introduction_machine_learning.md index 6a88a400..8dec6f69 100755 --- a/_i18n/ru/_course/introduction_machine_learning.md +++ b/_i18n/ru/_course/introduction_machine_learning.md @@ -1,34 +1,39 @@ ### О курсе + В курсе рассматриваются основные задачи обучения по прецедентам: классификация, кластеризация, регрессия, понижение размерности. Изучаются методы их решения, как классические, так и новые, созданные за последние 10–15 лет. Упор делается на глубокое понимание математических основ, взаимосвязей, достоинств и ограничений рассматриваемых методов. Теоремы в основном приводятся без доказательств. ### Тематический план -* Линейный классификатор и стохастический градиент. -* Метрические методы классификации и регрессии. -* Метод опорных векторов. -* Многомерная линейная регрессия. Нелинейная регрессия. -* Критерии выбора моделей и методы отбора признаков. -* Логические методы классификации. -* Линейные ансамбли. Продвинутые методы ансамблирования. -* Оценивание плотности и байесовская классификация. -* Кластеризация и частичное обучение. -* Нейронные сети глубокого обучения. -* Нейронные сети с обучением без учителя. -* Векторные представления текстов и графов. -* Модели внимания и трансформеры. -* Тематическое моделирование. -* Обучение ранжированию. -* Рекомендательные системы. -* Поиск ассоциативных правил. -* Адаптивные методы прогнозирования. -* Инкрементное и онлайновое обучение. -* Обучение с подкреплением. -* Активное обучение. + +- Линейный классификатор и стохастический градиент. +- Метрические методы классификации и регрессии. +- Метод опорных векторов. +- Многомерная линейная регрессия. Нелинейная регрессия. +- Критерии выбора моделей и методы отбора признаков. +- Логические методы классификации. +- Линейные ансамбли. Продвинутые методы ансамблирования. +- Оценивание плотности и байесовская классификация. +- Кластеризация и частичное обучение. +- Нейронные сети глубокого обучения. +- Нейронные сети с обучением без учителя. +- Векторные представления текстов и графов. +- Модели внимания и трансформеры. +- Тематическое моделирование. +- Обучение ранжированию. +- Рекомендательные системы. +- Поиск ассоциативных правил. +- Адаптивные методы прогнозирования. +- Инкрементное и онлайновое обучение. +- Обучение с подкреплением. +- Активное обучение. ### Самостоятельная работа + Нет. ### Оценивание + В конце курса студенты сдают устный экзамен по всем темам курса. + ### Требуемые знания Теория вероятностей, статистика, методы оптимизации, линейная алгебра. diff --git a/_i18n/ru/_course/natural_language_processing.md b/_i18n/ru/_course/natural_language_processing.md index be79a263..19ace401 100755 --- a/_i18n/ru/_course/natural_language_processing.md +++ b/_i18n/ru/_course/natural_language_processing.md @@ -1,27 +1,32 @@ ### О курсе + В курсе рассматриваются основные задачи и математические методы обработки естественного языка. ### Тематический план -* Предобработка, выделение признаков и классификация. -* Векторные представления слов. -* Задача разметки последовательностей (tagging). Модель Linear-CRF. -* Модели рекуррентных нейронных сетей: RNN, LSTM. -* Машинный перевод. Подход Sequence-to-sequence. Механизм внимания. -* Архитектура transformer. -* Задача языкового моделирования. -* Статистические и нейросетевые языковые модели. -* Задача генерации естественного языка. -* Контекстуальные векторные представления слов. -* Transfer learning в NLP. -* Модель BERT и её модификации. -* Задача классификации текстов. -* Тематическое моделирование и его приложения. + +- Предобработка, выделение признаков и классификация. +- Векторные представления слов. +- Задача разметки последовательностей (tagging). Модель Linear-CRF. +- Модели рекуррентных нейронных сетей: RNN, LSTM. +- Машинный перевод. Подход Sequence-to-sequence. Механизм внимания. +- Архитектура transformer. +- Задача языкового моделирования. +- Статистические и нейросетевые языковые модели. +- Задача генерации естественного языка. +- Контекстуальные векторные представления слов. +- Transfer learning в NLP. +- Модель BERT и её модификации. +- Задача классификации текстов. +- Тематическое моделирование и его приложения. ### Самостоятельная работа -В рамках курса предполагается четыре практических задания и экзамен. Срок выполнения каждого задания — 2 недели. За каждое задание можно получить до 10-ти баллов. За каждый день просрочки назначается штраф 1 балл. + +В рамках курса предполагается четыре практических задания и экзамен. Срок выполнения каждого задания — 2 недели. За каждое задание можно получить до 10-ти баллов. За каждый день просрочки назначается штраф 1 балл. ### Оценивание -0.7 * баллы за дз / 5 + 0.3 * баллы за экзамен. + +0.7 _ баллы за дз / 5 + 0.3 _ баллы за экзамен. ### Требуемые знания + Машинное обучение, основы глубинного обучения, языка программирования Python. diff --git a/_i18n/ru/_course/networks_text_analysis.md b/_i18n/ru/_course/networks_text_analysis.md index 751f356c..fb43d41b 100755 --- a/_i18n/ru/_course/networks_text_analysis.md +++ b/_i18n/ru/_course/networks_text_analysis.md @@ -1,27 +1,32 @@ ### О курсе + Рассматриваются методы и технологии, применяющиеся в интеллектуальном анализе данных (ИАД, data mining) и базирующиеся на понятиях сходства, близости, аналогии. Идея сходства свойственна человеческому мышлению, это породило целый комплекс подходов для всех фундаментальных задач ИАД, среди которых основное внимание в курсе уделено классификации, восстановлению регрессии, кластеризации, восстановлению пропущенных данных. Представлена теоретическая основа для построения, реализации и анализа широкого спектра моделей и методов ИАД. Рассмотрены методы построения и вычисления функций сходства, согласование сходства на различных множествах объектов, синтез новых способов сравнения объектов на базе уже имеющихся. Рассмотрен комплекс технологий, предназначенный для эффективного представления и обработки метрической информации вычислительными системами. Исследуются эвристические модели данных, описывающие исходную информацию об объектах распознавания на основе различных реализаций понятия сходства. Рассматриваются задачи, требующие решения при реализации указанных моделей. Изучаются специальные структуры данных и алгоритмы, позволяющие эффективно настраивать и использовать изучаемые модели. ### Тематический план -* Основные подходы к заданию сходства. -* Классическое определение метрики и метрического пространства. -* Локальные метрики и их продолжение на всё пространство. -* Геометрические подмножества общих метрических пространств. -* Примеры метрических пространств. -* Классификация функций сходства. -* Характеристики метрик. -* Преобразования метрик. -* Реализация метрик. -* Принцип самоорганизации. -* Метрики на конечных множествах. -* Разложение МК по конечным системам МК. + +- Основные подходы к заданию сходства. +- Классическое определение метрики и метрического пространства. +- Локальные метрики и их продолжение на всё пространство. +- Геометрические подмножества общих метрических пространств. +- Примеры метрических пространств. +- Классификация функций сходства. +- Характеристики метрик. +- Преобразования метрик. +- Реализация метрик. +- Принцип самоорганизации. +- Метрики на конечных множествах. +- Разложение МК по конечным системам МК. ### Самостоятельная работа + Нет. ### Оценивание + Устный экзамен по материалам курса. ### Требуемые знания + Машинное обучение, алгоритмы и структуры данных. diff --git a/_i18n/ru/_course/neural_architecture_search.md b/_i18n/ru/_course/neural_architecture_search.md index 9fc6706b..4054e3d9 100755 --- a/_i18n/ru/_course/neural_architecture_search.md +++ b/_i18n/ru/_course/neural_architecture_search.md @@ -1,25 +1,30 @@ ### О курсе + Курс посвящен современным методам построения сложных нейросетевых архитектур и выбору оптимальных структур. ### Тематический план -* Обзор типов нейросетей и описаний архитектур. -* Генетические алгоритмы от GMDH до WANN. -* Критерии качества выбора структур (обсудить через пару недель). -* Априорные предположения о структуре модели, виды распределений структурных параметров. -* Методы оптимизации структурных параметров. -* Онлайн-обучение и многорукие бандиты для порождения структур. -* Обучение с подкреплением для порождения структур. -* Передача знаний между нейросетями и оптимизация структурных параметров. -* Случайные процессы для порождения моделей. -* Порождающие состязательные сети и поиск структур. -* Порождение и отклонение структур. -* Двухуровневый байесовский выбор и семплирование Метрополиса-Хастингса. + +- Обзор типов нейросетей и описаний архитектур. +- Генетические алгоритмы от GMDH до WANN. +- Критерии качества выбора структур (обсудить через пару недель). +- Априорные предположения о структуре модели, виды распределений структурных параметров. +- Методы оптимизации структурных параметров. +- Онлайн-обучение и многорукие бандиты для порождения структур. +- Обучение с подкреплением для порождения структур. +- Передача знаний между нейросетями и оптимизация структурных параметров. +- Случайные процессы для порождения моделей. +- Порождающие состязательные сети и поиск структур. +- Порождение и отклонение структур. +- Двухуровневый байесовский выбор и семплирование Метрополиса-Хастингса. ### Самостоятельная работа -Лабораторная работа состоит в исследовании метода поиска архитектуры. Первая работа – проанализировать готовый метод, вторая работа – предложить и запрограммировать свой метод. Отчет о работе – страница текста с формальным описанием метода с детализацией, достаточной для восстановления кода, и анализом ошибки (базовые критерии сложность, устойчивость, точность). Интерфейс к классу фиксирован и общий для всех, так же как и выборки. Существует общая таблица с результатами, и частный анализ ошибки каждого метода. + +Лабораторная работа состоит в исследовании метода поиска архитектуры. Первая работа – проанализировать готовый метод, вторая работа – предложить и запрограммировать свой метод. Отчет о работе – страница текста с формальным описанием метода с детализацией, достаточной для восстановления кода, и анализом ошибки (базовые критерии сложность, устойчивость, точность). Интерфейс к классу фиксирован и общий для всех, так же как и выборки. Существует общая таблица с результатами, и частный анализ ошибки каждого метода. ### Оценивание -Всего 10 баллов, два балла за ответы на вопросы в течение лекций, по четыре балла за две лабораторные работы. Оценивается не точность аппроксимации, а качество кода и анализ ошибки. + +Всего 10 баллов, два балла за ответы на вопросы в течение лекций, по четыре балла за две лабораторные работы. Оценивается не точность аппроксимации, а качество кода и анализ ошибки. ### Требуемые знания + Машинное обучение, глубокое обучение, байесовский выбор моделей. diff --git a/_i18n/ru/_course/optimization_methods.md b/_i18n/ru/_course/optimization_methods.md deleted file mode 100755 index 7648cc38..00000000 --- a/_i18n/ru/_course/optimization_methods.md +++ /dev/null @@ -1,10 +0,0 @@ -### О курсе - -### Тематический план - -### Самостоятельная работа - -### Оценивание - -### Требуемые знания - diff --git a/_i18n/ru/_course/probabilistic_topic_models.md b/_i18n/ru/_course/probabilistic_topic_models.md index 3a95f91c..fce12177 100755 --- a/_i18n/ru/_course/probabilistic_topic_models.md +++ b/_i18n/ru/_course/probabilistic_topic_models.md @@ -1,25 +1,30 @@ ### О курсе + В спецкурсе изучается вероятностное тематическое моделирование (topic modeling) коллекций текстовых документов. Тематическая модель определяет, какие темы содержатся в большой текстовой коллекции, и к каким темам относится каждый документ. Тематические модели позволяют искать тексты по смыслу, а не по ключевым словам, и создавать информационно-поисковые системы нового поколения, основанные на парадигме семантического разведочного поиска (exploratory search). Рассматриваются тематические модели для классификации, категоризации, сегментации, суммаризации текстов естественного языка, а также для рекомендательных систем, анализа банковских транзакционных данных, анализа биомедицинских сигналов. В спецкурсе развивается многокритериальный подход к построению моделей с заданными свойствами — аддитивная регуляризация тематических моделей (АРТМ). Он основан на регуляризации некорректно поставленных задач стохастического матричного разложения. Особое внимание уделяется методам лингвистической регуляризации для моделирования связности текста. Предполагается проведение студентами численных экспериментов на модельных и реальных данных с помощью библиотеки тематического моделирования BigARTM. ### Тематический план -* Задача тематического моделирования. -* Онлайновый ЕМ-алгоритм и регуляризаторы. -* Разведочный информационный поиск. -* Оценивание качества тематических моделей. -* BigARTM и базовые инструменты. -* Теория ЕМ-алгоритма. -* Байесовское обучение модели LDA. -* Тематические модели сочетаемости слов. -* Анализ зависимостей. -* Мультимодальные тематические модели. -* Моделирование локального контекста. -* Суммаризация и визуализация. + +- Задача тематического моделирования. +- Онлайновый ЕМ-алгоритм и регуляризаторы. +- Разведочный информационный поиск. +- Оценивание качества тематических моделей. +- BigARTM и базовые инструменты. +- Теория ЕМ-алгоритма. +- Байесовское обучение модели LDA. +- Тематические модели сочетаемости слов. +- Анализ зависимостей. +- Мультимодальные тематические модели. +- Моделирование локального контекста. +- Суммаризация и визуализация. ### Самостоятельная работа + Нет. ### Оценивание + Условием сдачи курса является выполнение индивидуальных практических заданий. ### Требуемые знания + Линейная алгебра, математический анализ, теория вероятностей. diff --git a/_i18n/ru/_course/programming_practicum_python.md b/_i18n/ru/_course/programming_practicum_python.md new file mode 100755 index 00000000..33baa7d8 --- /dev/null +++ b/_i18n/ru/_course/programming_practicum_python.md @@ -0,0 +1,56 @@ +### О курсе + +Курс посвящен практическим навыкам программирования на Python с акцентом на приложения в области data science и машинного обучения. Особое внимание уделяется основам Python, инструментам анализа данных, нейронным сетям и практикам промышленной разработки. Цель курса — предоставить студентам комплексные навыки программирования на Python, необходимые для современного data science и ML-инжиниринга. + +### Тематический план + +Курс структурирован на три логических блока, охватывающих путь от базового Python до промышленных приложений: + +#### Блок 1: Введение в язык Python + +1. **Введение в Python**: Встроенные типы данных, модель памяти и основы языка +2. **Функции и итераторы**: Определение функций, итераторы, генераторы и продвинутые конструкции Python +3. **Объектно-ориентированное программирование I**: Возможности языка, атрибуты, наследование и принципы проектирования классов + +#### Блок 2: Python для машинного обучения + +4. **Инструменты анализа данных**: NumPy, Pandas, Matplotlib и основные библиотеки для работы с данными +5. **Инструменты машинного обучения**: Scikit-learn, обучение моделей, оценка качества и разработка ML-пайплайнов +6. **Объектно-ориентированное программирование II**: Типизация, полиморфизм, dataclass, декораторы и продвинутые концепции ООП +7. **Нейронные сети**: Фреймворки глубокого обучения, PyTorch/TensorFlow и реализация нейронных сетей + +#### Блок 3: Элементы промышленной разработки + +8. **Виртуальные окружения и контейнеры**: Управление окружениями, Docker и развертывание приложений +9. **Модули Python и веб-клиенты**: Система модулей, HTTP-клиенты и взаимодействие с API +10. **Серверная веб-разработка**: Flask/FastAPI, REST API и архитектура веб-сервисов +11. **Методы повышения эффективности кода**: Оптимизация производительности, профилирование и лучшие практики для production кода + +### Лекции и практические задания + +Курс сочетает теоретические лекции с практическими заданиями: + +- **Формат**: Интерактивные лекции + задания по программированию +- **Структура**: 11 лекций, охватывающих теоретические основы и практические реализации +- **Задания**: 4 комплексных практических задачи, строящиеся друг на друге + +### Самостоятельная работа + +4 практических задания, охватывающих полный цикл разработки на Python: + +1. **Введение в Python**: Базовые конструкции языка, структуры данных и основы программирования +2. **Анализ данных и машинное обучение**: Обработка данных, статистический анализ и реализация ML-моделей +3. **Нейронные сети**: Разработка моделей глубокого обучения, обучение и оценка качества +4. **Веб-сервер для ML-моделей**: Full-stack ML-приложение с возможностями обучения и inference + +### Оценивание + +Для прохождения курса и получения зачета студенты должны: + +- **Суммарный балл**: Набрать не менее 60 баллов из всех 4 заданий +- **Минимум за задание**: Набрать не менее 10 баллов за каждое отдельное задание +- **Максимальный балл**: 100 баллов всего (25 баллов за задание) + +### Требуемые знания + +Базовые знания программирования, математические основы (линейная алгебра, статистика) и знакомство с алгоритмическим мышлением. diff --git a/_i18n/ru/_course/recommender_systems.md b/_i18n/ru/_course/recommender_systems.md index c69c0105..f3b64534 100644 --- a/_i18n/ru/_course/recommender_systems.md +++ b/_i18n/ru/_course/recommender_systems.md @@ -1,7 +1,9 @@ ### О курсе + Курс посвящен рекомендательным системам. Мы рассмотрим основные теоретические и прикладные аспекты задачи рекомендаций. В конце немного затронем применение многоруких бандитов для рекомендаций и специфические вопросы оценивания рекомендательных систем. ### Тематический план + 1. Задача рекомендаций 2. Модели, основанные на методе ближайших соседей 3. Матричная факторизация @@ -12,10 +14,13 @@ 8. Оффлайн-оценивание рекомендаций ### Cамостоятельная работа + Два домашних задания по ходу курса ### Оценивание + По результатам домашних заданий ### Требуемые знания + Машинное обучение, глубокое обучение diff --git a/_i18n/ru/_course/rnd_in_ai.md b/_i18n/ru/_course/rnd_in_ai.md index 435ff125..640f467f 100644 --- a/_i18n/ru/_course/rnd_in_ai.md +++ b/_i18n/ru/_course/rnd_in_ai.md @@ -1,20 +1,23 @@ ### О курсе + Курс является расширением курса ``Автоматизация научных исследований’’. Работа производится в командах — 2-3 человека. Курс предполагает еженедельные презентации работы команды за неделю: 5 минут презентация + 5 минут обсуждение с другими людьми. **Критерий к проекту:** + 1. Весь проект должен быть на GitHub под OpenSource лицензией (MIT) 2. Проект должен содержать код и инструкция по его запуску. - 1. Базовый код в jupyter notebook для демонстрации концепции работы и построения графиков из статьи — должен запускаться с colab. - 2. Исходный код вычислительного эксперимента должен запускаться на Unix системе выполнением двух команд (возможно в специльном docker образе): - * python3 train.py — для обучения моделей. - * python3 test.py — для тестирования, получения результатов эксперимента. - 3. Документация к коду — sphinx. + 1. Базовый код в jupyter notebook для демонстрации концепции работы и построения графиков из статьи — должен запускаться с colab. + 2. Исходный код вычислительного эксперимента должен запускаться на Unix системе выполнением двух команд (возможно в специльном docker образе): + - python3 train.py — для обучения моделей. + - python3 test.py — для тестирования, получения результатов эксперимента. + 3. Документация к коду — sphinx. 3. Проект должен содержать рукопись статьи используя стилевик от arXiv — для унификации. 4. Если проект подразумевает не синтетические данные, то должна быть инструкция для получения этих данных, а также скрипт для их получения. Если данные специфичные, то их требуется выложить на одном из файловых хранилищ. ### Тематический план + 1. Вводная лекция. 2. Обсуждения проектов. 3. Правильная структура проекта. @@ -31,9 +34,11 @@ 14. Проверка проектов и зачет. ### Самостоятельная работа + Написание статьи в рамках команды. ### Grading + В курсе 4 чекпоинтов, за каждый дается 3 балла Исследование предметной области — анализ проблемы. Получение теоретических результатов. @@ -41,4 +46,5 @@ Проект на гитхабе. ### Требуемые знания -Машинное обучение, глубокое обучение, программирование на питоне. \ No newline at end of file + +Машинное обучение, глубокое обучение, программирование на питоне. diff --git a/_i18n/ru/_course/signal_processing.md b/_i18n/ru/_course/signal_processing.md index c77c63a7..3938a857 100755 --- a/_i18n/ru/_course/signal_processing.md +++ b/_i18n/ru/_course/signal_processing.md @@ -1,22 +1,27 @@ ### О курсе + Курс посвящен использованию методов математического моделирования и теоретической физики в задачах обработки сигналов. На примерах изображений, видео, звука и других сигналов рассматриваются методы выбора моделей машинного обучения. Обсуждаются приемы построения систем моделей для разнородных сигналов. ### Тематический план -* Ядра и метрические пространства, RKHS для визуализации томограмм. -* Сферические гармоники и моделирование механического движения. -* Риманова геометрия на формах и диффеоморфизмы для fMRI. -* Многообразия, связность Леви-Чивиты и тензоры кривизны. -* Дифференциальные формы и пучки с примерами. -* Уравнения Навье-Стокса и вязкое течение. -* Геометрическая алгебра, внешнее произведение и кватернионы. -* Спектр графа, непрерывные операторы Лапласа, диффузионные модели. -* Гомологии и когомологии, дифференциальные формы для построения ансамблей моделей. + +- Ядра и метрические пространства, RKHS для визуализации томограмм. +- Сферические гармоники и моделирование механического движения. +- Риманова геометрия на формах и диффеоморфизмы для fMRI. +- Многообразия, связность Леви-Чивиты и тензоры кривизны. +- Дифференциальные формы и пучки с примерами. +- Уравнения Навье-Стокса и вязкое течение. +- Геометрическая алгебра, внешнее произведение и кватернионы. +- Спектр графа, непрерывные операторы Лапласа, диффузионные модели. +- Гомологии и когомологии, дифференциальные формы для построения ансамблей моделей. ### Самостоятельная работа + Две персональных лабораторных работы по анализу видеоряда с постановкой задачи и вычислительным экспериментом. Отчет состоит из двухстраничного описания результатов, кода и доклада. ### Оценивание + Вопросы в течение занятий (3), две лабораторные работы (2+2), экзамен в конце с обсуждением тем и задач (3). ### Требуемые знания + Знание алгебры, математического анализа и общей физики в объеме бакалавриата ФУПМ МФТИ. diff --git a/_i18n/ru/_course/software_engineering_data_analysis.md b/_i18n/ru/_course/software_engineering_data_analysis.md index ff98f0cd..d43a29a0 100755 --- a/_i18n/ru/_course/software_engineering_data_analysis.md +++ b/_i18n/ru/_course/software_engineering_data_analysis.md @@ -1,24 +1,30 @@ ### О курсе + В курсе рассматриваются вопросы разработки систем обработки данных и машинного обучения. -* Как вывести разработанную модель в продакшен? -* Что делать для совместной работы над наукоемким ПО? -* Как не потерять ранее достигнутые исследовательские результаты? + +- Как вывести разработанную модель в продакшен? +- Что делать для совместной работы над наукоемким ПО? +- Как не потерять ранее достигнутые исследовательские результаты? В результате освоения курса слушатели приобретают навыки промышленной разработки алгоритмов машинного обучения, проведения повторяемых экспериментов, использования больших данных, тестирования и процессов выполнения проектов в области машинного обучения. ### Тематический план -* Структурирование программ обработки данных (CODE). -* Написание надежного кода (CODE). -* Проектирование систем и хранение данных в системах машинного обучения (DATA). -* Процессы и виды работ в проекте анализа данных (PROC). -* Обеспечение повторяемости результатов (PROC). -* Тестирование наукоемкого ПО (TEST). + +- Структурирование программ обработки данных (CODE). +- Написание надежного кода (CODE). +- Проектирование систем и хранение данных в системах машинного обучения (DATA). +- Процессы и виды работ в проекте анализа данных (PROC). +- Обеспечение повторяемости результатов (PROC). +- Тестирование наукоемкого ПО (TEST). ### Самостоятельная работа + Практические задания по ходу курса + курсовой проект. ### Оценивание + Итоговая оценка по курсу формируется из успешности выполнения заданий по ходу семестра - по 10% за каждое задание, и подтверждение на устном опросе владения каждой из тем курса (CODE, TEST, DATA, PROC) - 40% оценки. ### Требуемые знания + Python. diff --git a/_i18n/ru/_people/beznosikov_an.md b/_i18n/ru/_people/beznosikov_an.md deleted file mode 100644 index c73b5e52..00000000 --- a/_i18n/ru/_people/beznosikov_an.md +++ /dev/null @@ -1,9 +0,0 @@ -Окончил TODO в TODO, в TODO защитил диссертацию по TODO, кандидат физико-математических наук. Автор более TODO научных работ по TODO. - -**Профессональные интересы:** TODO. - - - -### Основные публикации -1. TODO -2. TODO diff --git a/_i18n/ru/_people/dorin_dd.md b/_i18n/ru/_people/dorin_dd.md new file mode 100644 index 00000000..60778ac8 --- /dev/null +++ b/_i18n/ru/_people/dorin_dd.md @@ -0,0 +1,3 @@ +Окончил бакалавриат МФТИ с отличием в 2024 году и в настоящее время является студентом магистратуры кафедры Интеллектуальных систем. Автор более 5 научных работ в области компьютерного зрения, интерфейсов мозг-компьютер и оптимизации. + +**Профессиональные интересы:** компьютерное зрение, интерфейсы мозг-компьютер. diff --git a/_i18n/ru/_people/firsov_sa.md b/_i18n/ru/_people/firsov_sa.md new file mode 100644 index 00000000..6e1d6202 --- /dev/null +++ b/_i18n/ru/_people/firsov_sa.md @@ -0,0 +1,3 @@ +Окончил бакалавриат МФТИ в 2025 году и в настоящее время является студентом магистратуры кафедры Интеллектуальных систем. Публикует 3 научные работы в области машинного обучения и преподает в МФТИ. + +**Профессиональные интересы:** компьютерное зрение, агентные системы, большие языковые модели. diff --git a/_i18n/ru/_people/kasyuk_va.md b/_i18n/ru/_people/kasyuk_va.md new file mode 100644 index 00000000..4faa7a9e --- /dev/null +++ b/_i18n/ru/_people/kasyuk_va.md @@ -0,0 +1,3 @@ +Окончил бакалавриат МФТИ в 2025 году и в настоящее время является студентом магистратуры кафедры Интеллектуальных систем. + +**Профессиональные интересы:** генеративные модели, обучение с подкреплением, большие языковые модели. diff --git a/_i18n/ru/_people/kiselev_ns.md b/_i18n/ru/_people/kiselev_ns.md new file mode 100644 index 00000000..acb1d53f --- /dev/null +++ b/_i18n/ru/_people/kiselev_ns.md @@ -0,0 +1,3 @@ +Окончил бакалавриат МФТИ с отличием в 2024 году и в настоящее время является студентом магистратуры кафедры Интеллектуальных систем. Автор более 6 научных работ в области компьютерного зрения и оптимизации. + +**Профессиональные интересы:** генеративный искусственный интеллект, компьютерное зрение, оптимизация. diff --git a/_i18n/ru/_people/kreinin_mv.md b/_i18n/ru/_people/kreinin_mv.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/ru/_people/kreinin_mv.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/ru/_people/morozov_ma.md b/_i18n/ru/_people/morozov_ma.md new file mode 100644 index 00000000..4b7ddd64 --- /dev/null +++ b/_i18n/ru/_people/morozov_ma.md @@ -0,0 +1,3 @@ +Окончил с отличием МФТИ и Сколтех в 2022 году. В 2023 году начал аспирантуру в KAUST, где занимался 3D, глубоким обучением и компьютерным зрением под руководством профессора Питера Вонки. + +**Профессиональные интересы:** глубокие генеративные модели, 3D компьютерное зрение. diff --git a/_i18n/ru/_people/nikitina_ma.md b/_i18n/ru/_people/nikitina_ma.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/ru/_people/nikitina_ma.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/ru/_people/panchenko_sk.md b/_i18n/ru/_people/panchenko_sk.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/ru/_people/panchenko_sk.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/ru/_people/vladimirov_ea.md b/_i18n/ru/_people/vladimirov_ea.md new file mode 100644 index 00000000..1333ed77 --- /dev/null +++ b/_i18n/ru/_people/vladimirov_ea.md @@ -0,0 +1 @@ +TODO diff --git a/_i18n/ru/_people/yakovlev_kd.md b/_i18n/ru/_people/yakovlev_kd.md index 0b57275c..b91f4092 100644 --- a/_i18n/ru/_people/yakovlev_kd.md +++ b/_i18n/ru/_people/yakovlev_kd.md @@ -1,4 +1,3 @@ -Окончил бакалавриат и магистратуру [МФТИ](https://mipt.ru) в 2024 году. -С 2024 является аспирантом кафедр интеллектуальных систем и МОУ. +Окончил магистратуру МФТИ в 2024 году с отличием. В настоящее время является аспирантом кафедры Интеллектуальных систем. -**Профессиональные интересы:** TODO +**Профессиональные интересы:** статистическая теория обучения. diff --git a/_i18n/ru/_posts/2025-10-30-new-website.md b/_i18n/ru/_posts/2025-10-30-new-website.md new file mode 100644 index 00000000..0506f19d --- /dev/null +++ b/_i18n/ru/_posts/2025-10-30-new-website.md @@ -0,0 +1,19 @@ +--- +layout: news +title: "Новый дизайн сайта" +date: 2025-10-30 +excerpt: "Мы представляем новый дизайн нашего сайта, обновленный для улучшения пользовательского опыта и доступности." +lang: ru +important: false +--- + +Кафедра интеллектуальных систем обновила свой сайт, чтобы улучшить пользовательский опыт и доступность. + +Ключевые особенности: + +1. Раздел новостей для последних обновлений +2. Улучшенное меню навигации +3. Удобный для мобильных устройств дизайн +4. Страница-лэндинг для новых посетителей +5. Шаблоны для написания статей, отчетов и дипломных работ +6. Календарь сроков конференций diff --git a/_i18n/ru/_posts/2025-10-31-admission.md b/_i18n/ru/_posts/2025-10-31-admission.md new file mode 100644 index 00000000..f46e1c83 --- /dev/null +++ b/_i18n/ru/_posts/2025-10-31-admission.md @@ -0,0 +1,10 @@ +--- +layout: news +title: "Поступление на кафедру" +date: 2025-10-31 +excerpt: "Собеседование пройдет 1 ноября в 13:00, онлайн в Zoom." +lang: ru +important: true +--- + +Кафедра интеллектуальных систем проведет собеседование для поступающих 1 ноября в 13:00, онлайн в Zoom: [m1p.org/go_zoom](https://m1p.org/go_zoom). diff --git a/_i18n/ru/about.md b/_i18n/ru/about.md deleted file mode 100644 index 11d0b3a4..00000000 --- a/_i18n/ru/about.md +++ /dev/null @@ -1,59 +0,0 @@ -### Кафедра интеллектуальных систем -Физтех-школа прикладной математики и информатики МФТИ - -Базовая кафедра выпускает бакалавров и магистров по направлению 010900 «Прикладные математика и физика». Обучение на кафедре ведется по трем специализациям «Интеллектуальный анализ данных», «Проектирование и организация систем», «Информационный поиск и машинное обучение». Базовая организация – Вычислительный центр ФИЦ “Информатика и управление” Российской академии наук. - -Базовая организация – Вычислительный центр РАН, ФИЦ «Информатика и управление» Российской академии наук. Создана академиком РАН и выдающимся российским математиком, специалистом в области математических методов распознавания, прогнозирования и интеллектуального анализа данных [Константином Владимировичем Рудаковым](https://ru.wikipedia.org/wiki/Рудаков,_Константин_Владимирович). Кафедра активно развивается с 2003 года в рамках научной школы академика РАН [Юрия Ивановича Журавлева](https://ru.wikipedia.org/wiki/Журавлёв,_Юрий_Иванович_(математик)). Существенный вклад в развитие кафедры внесли профессор РАН, д.ф.-м.н. [К.В. Воронцов](https://ru.wikipedia.org/wiki/Воронцов,_Константин_Вячеславович) и д.ф.-м.н. В.В. Стрижов. - -### Преподаватели кафедры -[20 исследователей](/ru/people/): профессор РАН, доктора и кандидаты наук. Преподаватели – молодые кандидаты наук, выпускники кафедры к.ф.-м.н. [Александр Адуенко](/ru/people/aduenko_aa/index.html), к.ф.-м.н. [Олег Бахтеев](/ru/people/bakhteev_oy/index.html), к.ф.-м.н. [Роман Исаченко](/ru/people/isachenko_rv/index.html), соискатель к.ф.-м.н. [Андрей Грабовой](/ru/people/grabovoy_av/index.html). Средний возраст преподаватетей 35 лет. - -### Направления учебной и научной деятельности кафедры -Машинное обучение; многомерная статистика; геометрические методы глубокого обучения; выбор моделей и нейросетевых архитектур; ансамбли моделей и порождающие нейросети; функциональный анализ данных и анализ пространственно-временных данных. - -### Прикладные исследования -Анализ текстов и тематическое моделирование, анализ изображений и видео, анализ многомерных временных рядов, анализ биомедицинских сигналов, интерфейсы мозг-компьютер. - -### Принципы научной работы -Открытость идей, проектов, результатов на всех стадиях учебы и исследований; постоянная оценка качества идей и результатов; связь с научным сообществом, обновление согласно последним достижениям. - -### Основные курсы -***Машинное обучение*** читает К.В. Воронцов – наиболее известный в России и полный курс, включающий фундаментальные и современные темы машинного обучения и анализа данных. - -***Моя первая научная статья: автоматизация научных исследований*** читает В.В. Стрижов – курс, дающий основы выполнения научных исследований – от планирования до представления результатов. Каждый студент выбирает персональный проект и получает личного консультанта и эксперта. В течение трех месяцев студент готовит научную статью с теорией и вычислительным экспериментом. Результаты представляются на научных конференциях, статьи подаются в рецензируемые журналы. - -### Основные курсы ([программы](/ru/course/)) -- Машинное обучение -- Автоматизация научных исследований -- Методы глубокого обучения -- Выбор моделей машинного обучения -- Математические методы прогнозирования -- Порождающие модели машинного обучения -- Байесовское мультимоделирование -- Тематические моделирование -- Математические методы анализа текстов -- Анализ данных в метрических пространствах -- Обработка сигналов -- Биоинформатика -- Технологии программной инженерии -- Рекоммендательные системы - -### Стипендии -- [Научная академическая стипендия им. К.В. Рудакова](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/Stipendia_im_Rudakova.pdf) присваивается студентам бакалавриата и магистратуры за успехи в учебе и исследовательской деятельности. Спонсор Форексис ГК. - -### Совместные учебные программы -В 2019 году кафедрой организована программа двойных дипломов и совместной магистратуры в Университете Гренобль-Альпы. Студенты магистратуры обучаются по совместным программам в Парижской политехнической школе, Сколковском институте науки и технологий, Научно-технологическом университете KAUST. Ведутся совместные исследования с лабораториями UGA, INRIA, CNRS, Ecole Polytechnique, EPFL, Los-Alamos, CMU. -- [Master program in Operations Research, Combinatorics and Optimization](https://master-informatique.univ-grenoble-alpes.fr/main-menu/academic-program/operations-research-combinatorics-optimisation/operations-research-combinatorics-optimisation-79396.kjsp?RH=1467388092289), [страница МФТИ](https://mipt.ru/education/joint_programs/ecolepolytech/) -- [Master of Science in Informatics at Grenoble](https://master-informatique.univ-grenoble-alpes.fr/main-menu/academic-program/master-of-science-mosig/), [страница МФТИ](https://mipt.ru/education/joint_programs/grenoble.php) -- [Cycle Ingeneur at Ecole Polytechnique](https://www.polytechnique.edu/admission-cycle-ingenieur/en), [страница МФТИ](https://mipt.ru/education/joint_programs/grenoble.php) - -### Стажировки -Кафедра с момента своего основания активно сотрудничает с базовыми компаниями группы Форексис ГК: Форексис, Антиплагиат, Антирутина, Гудфокаст, Лаборатория труда, Прокомплаенс и участвует в совместных проектах Форексис ГК с компаниями ММФБ, ИнтерРАО, Яндекс, Сбер, РЖД, Samsung, LG. -- Форексис: [анализ временных рядов, финансовая аналитика, анализ новостных потоков](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/Forecsys_Intern.pdf) -- Антиплагиат: [анализ текстов](https://www.antiplagiat.ru/) -- INRIA National Institute for Research in Digital Science and Technology: [Bioinformatics](https://team.inria.fr/nano-d/job-openings/) - -### Приходите к нам учиться и заниматься научными исследованиями в области машинного обучения! -- [О поступлении](/ru/admission/) -- [Скачать страницу о кафедре](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/Intelligent_Systems_MIPT.pdf) -- [Скачать презентацию о кафедре](https://github.com/Intelligent-Systems-Phystech/intelligent-systems-phystech.github.io/raw/master/images/IS_Slides.pdf) diff --git a/_i18n/ru/admission.md b/_i18n/ru/admission.md index 6c7cc739..a28d832f 100644 --- a/_i18n/ru/admission.md +++ b/_i18n/ru/admission.md @@ -1,46 +1,127 @@ -## Слушателям отдельных курсов -1. Приходите, слушайте, участвуйте. -2. Вся информация о текущих курсах доступна в [канале](https://t.me/IS_MIPT). +## Поступление на кафедру + +На этой странице вы найдете информацию о процедуре поступления на кафедру Интеллектуальных систем МФТИ, включая детали для слушателей отдельных курсов, процедуру собеседования для бакалавров, процесс поступления в магистратуру и научную работу на кафедре. + +**Слушателям отдельных курсов** + +1. Приходите, слушайте, участвуйте. +2. Вся информация о текущих курсах доступна в [канале]({{site.telegram}}). 3. Ведомости на кафедру идут из деканата, оформляйте их там. 4. Курсы требуют подготовки, поэтому - - уточните у преподавателей возможность присоединиться к курсу, - - в течение первых недель поймите, сможете ли вы сдать курс. -5. Узнайте, что требуется для сдачи курса. - - - - - - -## Поступление на кафедру -**Формат поступления:** собеседование - -### Алгоритм поступления, 2-3 курсы, бакалавры - -1. студент заполняет [анкету](http://bit.ly/1lFrFha), -2. решает одну из нижеприведенных задач (четвертый курс рассказывает о дипломной работе), -3. составляет мнение о работах, которые выполняют студенты кафедры, -4. в назначенную дату делает трехминутный доклад о задаче и о заинтересовавшей теме или работе, -5. в тот же день вечером получает решение кафедры, -6. ждет распоряжение деканата о распределении на кафедру. - -### Процедура собеседования 3 курса с точки зрения преподавателей -1. cобираем всю группу желающих поступить на кафедру, -2. слушаем краткий доклад каждого участника - - «решение тестовой задачи», - - «мои цели при поступлении на кафедру» на материале студенческих работ кафедры, -3. задаем вопросы, смотрим анкету, -4. составляем ранжированный список поступающих, публикуем [по ссылке тут] и отправляем в деканат. + - Уточните у преподавателей возможность присоединиться к курсу, + - В течение первых недель поймите, сможете ли вы сдать курс. +5. Узнайте, что требуется для сдачи курса. + +### Алгоритм поступления, 2-3 курсы, бакалавры + +1. Студент заполняет [анкету](http://bit.ly/1lFrFha), +2. Решает одну из нижеприведенных задач (четвертый курс рассказывает о дипломной работе), +3. Составляет мнение о работах, которые выполняют студенты кафедры ([Дипломные работы]({{ site.baseurl }}/materials/thesis), [отчеты НИР]({{ site.baseurl }}/materials/nir)), +4. В назначенную дату делает трехминутный доклад о задаче и о заинтересовавшей теме или работе, +5. В тот же день вечером получает решение кафедры, +6. Ждет распоряжение деканата о распределении на кафедру. + + + +### Задачи для поступления + +#### Осень 2025 + +
+

Задача 64

+

+ Визуализировать алгоритм Гершберга-Сакстона для двумерных изображений. Рассказать о двумерном преобразовании Фурье, об исходном и целевом пространствах и о сходимости в них. +

+
+ +
+

Задача 63

+

+ Рассказать о способах численного решения обыкновенных дифференциальных уравнений с иллюстрациями на реальных данных измерений. Желательно включить Adjoint State Method. +

+
+ +
+

Задача 62

+

+ Рассказать о методе Галеркина на примере реальных данных. Заменить линейную модель на двухслойную нейросеть. Показать разницу в решении. Визуализировать данные и модель. +

+
+ +
+

Задача 61

+

+ Рассказать о методе конечных элементов на с примером на реальных данных (уравнение эластичности, Пуассона, другие уравнения в частных производных по вашему выбору). Визуализировать различные подходы, для линейных моделей и нейросетей. +

+
+ +
+

Задача 60

+

+ Проиллюстрировать алгоритм снижения размерности пространства в методе Галеркина при решении уравнения Навье-Стокса с иллюстрацией на реальных или синтетических данных. +

+
+ +
+

Задача 59

+

+ Проиллюстрировать алгоритм снижения размерности на данных двумерной компьютерной томографии, линейная модель (и нейросеть по выбору). +

+
+ +
+

Задача 58

+

+ Рассказать о прогнозировании сегмента временного ряда методом сингулярного анализа спектра (английская версия). Проанализировать исходную размерность матрицы Ганкеля и ее сниженную размерность. +

+
+ +
+

Задача 57

+

+ Рассказать о том, чем преобразование Фурье более высоких порядков (с тензорным представлением данных) отличается от одномерного преобразования. Проиллюстрировать мультфильмом низкого разрешения (или похожими данными; в прямом и обратном преобразовании со снижением качества). +

+
+ +
+

Задача 56

+

+ Сравнить классические методы численного решения уравнений в частных производных (эллиптических, параболических, гиперболических) и нейросетевые приближения решений на реальных данных. +

+
+ +
+

Задача 55

+

+ Задан временной ряд IMU мобильного телефона (акселерометр, гироскоп). Телефон лежит на груди человека. Предложить алгоритм декомпозиции почти-периодических колебаний (пульс, дыхание, случайные движения). +

+
+ +
+

Задача 54

+

+ Задано два временных ряда, определить, являются ли они связанными (causal inference), с помощью метода Сходящихся перекрестных отображений. Проанализировать размерности пространств. +

+
+ +#### Задачи прошлых лет + +[Задачи прошлых лет](http://www.machinelearning.ru/wiki/index.php?title=%D0%9F%D1%80%D0%BE%D0%B1%D0%BD%D1%8B%D0%B5_%D0%B7%D0%B0%D0%B4%D0%B0%D1%87%D0%B8) также можно использовать для доклада. ### Советы по решению задач (это просто советы, а не указания) + - Теоретическое решение важнее практического. - Пишите теорию сами (не копируйте материал лекций). - Визуализируйте решение задач (рисунок от руки предпочтительнее его отсутствия). @@ -49,61 +130,68 @@ - Берите эти, или прошлые, или свои задачи – что вам самим интересно. ### Список тем для обсуждения -[Собран в разделе Список тем на этой странице](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%9F%D1%80%D0%B8%D0%B5%D0%BC_%D1%81%D1%82%D1%83%D0%B4%D0%B5%D0%BD%D1%82%D0%BE%D0%B2#.D0.A1.D0.BF.D0.B8.D1.81.D0.BE.D0.BA_.D1.82.D0.B5.D0.BC_.D0.B4.D0.BB.D1.8F_.D0.BA.D1.80.D0.B0.D1.82.D0.BA.D0.B8.D1.85_.D0.B4.D0.BE.D0.BA.D0.BB.D0.B0.D0.B4.D0.BE.D0.B2) -### Результаты отбора -- Публикуются на следующий день после отбора в канале кафедры [@IS_MIPT](https://t.me/IS_MIPT). +[Собран в разделе Список тем на этой странице](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%9F%D1%80%D0%B8%D0%B5%D0%BC_%D1%81%D1%82%D1%83%D0%B4%D0%B5%D0%BD%D1%82%D0%BE%D0%B2#.D0.A1.D0.BF.D0.B8.D1.81.D0.BE.D0.BA_.D1.82.D0.B5.D0.BC_.D0.B4.D0.BB.D1.8F_.D0.BA.D1.80.D0.B0.D1.82.D0.BA.D0.B8.D1.85_.D0.B4.D0.BE.D0.BA.D0.BB.D0.B0.D0.B4.D0.BE.D0.B2) + +### Результаты отбора + +- Публикуются на следующий день после отбора в [канале кафедры]({{site.telegram}}). ## Процедура приема в магистратуру -1. студент заполняет [анкету](http://bit.ly/1lFrFha), -2. cобираем желающих поступить на кафедру по запросам от них, -3. смотрим анкету, дипломную работу, спрашиваем мнение о теме и работах студентов кафедры, задаем вопросы по [математической части](https://arxiv.org/abs/2206.13446) бакалаврской программы Разделы 1, 2, 3 из Pen and Paper Exercises in Machine Learning by Michael U. Gutmann -Цель собеседования – понять, -1. каков вклад студент внесет в научную работу кафедры -2. соответствует ли квалификация студента уровню планируемых диссетраций магистров. +1. Студент заполняет [анкету](http://bit.ly/1lFrFha), +2. Собираем желающих поступить на кафедру по запросам от них, +3. Смотрим анкету, дипломную работу, спрашиваем мнение о теме и работах студентов кафедры, задаем вопросы по [математической части](https://arxiv.org/abs/2206.13446) бакалаврской программы Разделы 1, 2, 3 из Pen and Paper Exercises in Machine Learning by Michael U. Gutmann + +Цель собеседования – понять, + +1. Каков вклад студент внесет в научную работу кафедры +2. Соответствует ли квалификация студента уровню планируемых диссертаций магистров. +## Научная работа на кафедре -## Научная работа на кафедре +Ваша научная квалификация – ваша основная цель на кафедре. Кафедра фокусируется на математических основах машинного обучения. Это означает, что ваша работа фокусируется на развитии теоретических методов. Вы получаете теоретические результаты. Практические приложения для иллюстрации ваших результатов в вычислительном эксперименте могут быть произвольными. -Ваша научная квалификация – ваша основная цель на кафедре. Кафедра фокусируется на математических основах машинного обучения. Это означает, что ваша работа фокусируется на развитии теоретических методов. Вы получаете теоретические результаты. Практические приложения для иллюстрации ваших результатов в вычислительном эксперименте могут быть произвольными. +Научное сотрудничество и обмен идеями являются основой научной работы. Не стесняйтесь писать исследователям и рассказывать о себе и своих результатах и планах. Цель научного руководителя для вас – показать верное направление для исследований, дать тему, поставить задачу в общем. Надо понимать, что руководитель работает в своей тематике. Как узнать тематику? В [scholar.google.com](https://scholar.google.com/scholar?q=Vadim+Strijov&hl=en&as_sdt=0%2C5&as_ylo=2022&as_yhi=2019) забить фамилию руководителя, посмотреть работы последних лет. Попросить у руководителя задачу. -Научное сотрудничество и обмен идеями являются основой научной работы. Не стесняйтесь писать исследователям и рассказывать о себе и своих результатах и планах. Цель научного руководителя для вас – показать верное направление для исследований, дать тему, поставить задачу в общем. Надо понимать, что руководитель работает в своей тематике. Как узнать тематику? В [scholar.google.com](https://scholar.google.com/scholar?q=Vadim+Strijov&hl=en&as_sdt=0%2C5&as_ylo=2022&as_yhi=2019) забить фамилию руководителя, посмотреть работы последних лет. Попросить у руководителя задачу. +Требования к научному руководителю: -Требования к научному руководителю:  -1) доктор или кандидат наук,  -2) работает в тематике кафедры и держит связь с кафедрой. +1. Доктор или кандидат наук, +2. Работает в тематике кафедры и держит связь с кафедрой. Кафедра не может назначить вам научного руководителя. Его надо найти путем общения и договоренности о совместной работе. Когда будете искать научных руководителей, рассказывайте о себе: каковы ваша квалификация, достижения, научные работы, планы. -Совет. Ищите научных руководителей в исследовательских группах. Если Вас интересуют -- тематическое моделирование, информационный поиск, анализ новостей, то это группа проф. Константина Вячеславовича Воронцова, -- математика, оптимизация, управление, математическое моделирование, то это группа проф. Александра Владимировича Гасникова, -- технологии создания систем искусственного интеллекта, анализ изображений и видео, то это группа проф. Ивана Алексеевича Матвеева, -- генеративные модели, геометрическое глубокое обучение, выбор моделей, анализ сигналов, то это группа проф. Вадима Викторовича Стрижова, -- чистая и дискретная математика, продвинутая комбинаторика, то это группа проф. Андрея Михайловича Райгородского. +**Совет.** Ищите научных руководителей в исследовательских группах. Если Вас интересуют -Найдите участников этих научных групп. Посмотрите тематику их научных статей последних лет. Составьте список соавторов. Посмотрите прикрепленный PDF. Напишите потенциальным руководителям. Важный совет. Свяжитесь со студентами и аспирантами Вашей специальности. Спросите их как они организуют работу с научными руководителями.  +- Тематическое моделирование, информационный поиск, анализ новостей, то это группа проф. Константина Вячеславовича Воронцова, +- Математика, оптимизация, управление, математическое моделирование, то это группа проф. Александра Владимировича Гасникова, +- Технологии создания систем искусственного интеллекта, анализ изображений и видео, то это группа проф. Ивана Алексеевича Матвеева, +- Генеративные модели, геометрическое глубокое обучение, выбор моделей, анализ сигналов, то это группа проф. Вадима Викторовича Стрижова, +- Чистая и дискретная математика, продвинутая комбинаторика, то это группа проф. Андрея Михайловича Райгородского. -Для быстрого представления начальных результатов постарайтесь принять участие в студенческих конференциях [пример](https://conf.mipt.ru). +Найдите участников этих научных групп. Посмотрите тематику их научных статей последних лет. Составьте список соавторов. Посмотрите прикрепленный PDF. Напишите потенциальным руководителям. Важный совет. Свяжитесь со студентами и аспирантами Вашей специальности. Спросите их как они организуют работу с научными руководителями. + +Для быстрого представления начальных результатов постарайтесь принять участие в студенческих конференциях ([пример](https://conf.mipt.ru)). ### Что надо сделать: + 1. Посмотреть кто был успешным научруком: -- [дипломные работы](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%A1%D1%82%D1%83%D0%B4%D0%B5%D0%BD%D1%82%D1%8B), -- [отчеты и формат НИР](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%9E%D1%82%D1%87%D0%B5%D1%82%D1%8B_%D0%9D%D0%98%D0%A0), -- [преподаватели кафедры](http://is-mipt.site), -- [защиты бакалаврских работ](https://www.youtube.com/watch?v=mmAacGSUvPQ), -- [защиты магистериских](https://www.youtube.com/watch?v=f4C9U59krTE), -- [защиты кандидатских](https://www.youtube.com/playlist?list=PLk4h7dmY2eYGO1lczVHclXnv0f-CvUkXO). + - [Дипломные работы](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%A1%D1%82%D1%83%D0%B4%D0%B5%D0%BD%D1%82%D1%8B), + - [Отчеты и формат НИР](http://www.machinelearning.ru/wiki/index.php?title=%D0%98%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82%D1%83%D0%B0%D0%BB%D1%8C%D0%BD%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B_%28%D0%BA%D0%B0%D1%84%D0%B5%D0%B4%D1%80%D0%B0_%D0%9C%D0%A4%D0%A2%D0%98%29/%D0%9E%D1%82%D1%87%D0%B5%D1%82%D1%8B_%D0%9D%D0%98%D0%A0), + - [Преподаватели кафедры](http://is-mipt.site), + - [Защиты бакалаврских работ](https://www.youtube.com/watch?v=mmAacGSUvPQ), + - [Защиты магистериских](https://www.youtube.com/watch?v=f4C9U59krTE), + - [Защиты кандидатских](https://www.youtube.com/playlist?list=PLk4h7dmY2eYGO1lczVHclXnv0f-CvUkXO). 2. Посоветоваться со студентами и аспирантами. Почитать [руководство](http://www.machinelearning.ru/wiki/index.php?title=%D0%9D%D0%B0%D1%83%D1%87%D0%BD%D0%BE-%D0%B8%D1%81%D1%81%D0%BB%D0%B5%D0%B4%D0%BE%D0%B2%D0%B0%D1%82%D0%B5%D0%BB%D1%8C%D1%81%D0%BA%D0%B0%D1%8F_%D1%80%D0%B0%D0%B1%D0%BE%D1%82%D0%B0_%28%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%86%D0%B8%D0%B8%29). -3. Найти научного руководителя (по вашему стилю мышления и интересам).  -4. Попросить его **связаться с кафедрой** и утвердить тему работы.  -5. Начать работу с ним и представить ее результаты на зачетной неделе в начале сессии.  -6. Формат отчетности [статья, презентация, код](https://intsystems.github.io/ru/materials/nir/). +3. Найти научного руководителя (по вашему стилю мышления и интересам). +4. Попросить его **связаться с кафедрой** и утвердить тему работы. +5. Начать работу с ним и представить ее результаты на зачетной неделе в начале сессии. +6. Формат отчетности [статья, презентация, код]({{ site.baseurl }}/materials/nir). + +### Когда надо это сделать: -### Когда надо это сделать: 1. Третий курс ищет научруков в течение весеннего семестра и сообщает об этом на зачете то НИР. 2. Пятый курс имеет научрука в начале осеннего семестра (мы спрашиваем о планах). 3. Аспиранты имеют публикации с научруком. -Совет. Менять научрука и тему в любой момент – это нормально: вы развиваетесь, приоритеты изменяются. Желательно доделывать проекты, чтобы было что показать. Работать с несколькими научруками по разным темам – замечательно (если успеваете). Работать в командах – прекрасно, важен ваш личный вклад. +**Совет.** Менять научрука и тему в любой момент – это нормально: вы развиваетесь, приоритеты изменяются. Желательно доделывать проекты, чтобы было что показать. Работать с несколькими научруками по разным темам – замечательно (если успеваете). Работать в командах – прекрасно, важен ваш личный вклад. diff --git a/_i18n/ru/education.md b/_i18n/ru/education.md new file mode 100644 index 00000000..1eabe703 --- /dev/null +++ b/_i18n/ru/education.md @@ -0,0 +1,100 @@ +## Расписание + +**Онлайн занятия:** + +- Бакалавриат: [m1p.org/go_zoom](https://m1p.org/go_zoom) +- Магистратура: [m1p.org/go_zoom2](https://m1p.org/go_zoom2) +- YouTube: [youtube.com/@MachineLearningPhystech](https://www.youtube.com/@MachineLearningPhystech) + +**Документы и ссылки:** + +- Расписание института: [link](https://mipt.ru/upload/%D0%A3%D1%87%D0%B5%D0%B1%D0%BD%D0%BE%D0%B5%20%D1%83%D0%BF%D1%80%D0%B0%D0%B2%D0%BB%D0%B5%D0%BD%D0%B8%D0%B5/%D0%A0%D0%B0%D1%81%D0%BF%D0%B8%D1%81%D0%B0%D0%BD%D0%B8%D0%B5%20%D1%81%D0%B5%D1%81%D1%81%D0%B8%D0%B8/%D0%9B%D0%95%D0%A2%D0%9E%202023-2024/%D0%93%D1%80%D0%B0%D1%84%D0%B8%D0%BA%20%D1%83%D1%87%D0%B5%D0%B1%D0%BD%D0%BE%D0%B3%D0%BE%20%D0%BF%D1%80%D0%BE%D1%86%D0%B5%D1%81%D1%81%D0%B0%20%D0%BD%D0%B0%20%D1%81%D0%B0%D0%B9%D1%82.docx.pdf) +- Шаблон отчета НИР: [link](https://docs.google.com/document/d/1XsYWC7isbiums9jqjzddHIkDjvxqKNvf/edit?usp=sharing) +- Программа госэкзамена для 6 курса: [link](https://docs.google.com/document/d/1KkePnIg2BOf_LHBLBbgRL0W4gqKtt1W0OhJSg43lR_Y/edit?usp=sharing) + +### Осень 2025 + +#### Важные даты + +- **2 сентября:** Крайний срок подачи заявок на [стипендию]({{ site.baseurl }}/materials/scholarship) +- **6 сентября:** Начало занятий на кафедре +- **11-12 сентября:** Организационное собрание +- **23 октября:** Презентация кафедры для студентов 3 курса +- **1 ноября:** Собеседование для студентов 3 курса, поступающих на кафедру +- **15-21 декабря:** Экзаменационная неделя для студентов 3-6 курсов +- **21 декабря:** ❗️ Зачет по исследовательской работе (быть готовым с докладом/кодом/презентацией) +- **17 января:** Государственный экзамен для студентов 6 курса + +#### 4 курс, 7 семестр (вторник) + +| Время | Дисциплина | Преподаватели | Форма итоговой аттестации | Зачетные единицы | +| ----------- | -------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------- | ---------------- | +| 10:30-12:00 | [Методы глубокого обучения: Лекция]({{ site.baseurl }}/course/deep_learning) | [Эдуард Владимиров]({{ site.baseurl }}/people/vladimirov_ea), [Даниил Дорин]({{ site.baseurl }}/people/dorin_dd), [Никита Киселев]({{ site.baseurl }}/people/kiselev_ns), [Сергей Фирсов]({{ site.baseurl }}/people/firsov_sa), [Вадим Касюк]({{ site.baseurl }}/people/kasiuk_va) | Дифференцированный зачет | 2 | +| 12:10-13:40 | [Методы глубокого обучения: Семинар]({{ site.baseurl }}/course/deep_learning) | [Эдуард Владимиров]({{ site.baseurl }}/people/vladimirov_ea), [Даниил Дорин]({{ site.baseurl }}/people/dorin_dd), [Никита Киселев]({{ site.baseurl }}/people/kiselev_ns), [Сергей Фирсов]({{ site.baseurl }}/people/firsov_sa), [Вадим Касюк]({{ site.baseurl }}/people/kasiuk_va) | | | +| 14:30-16:00 | [Байесовский выбор моделей]({{ site.baseurl }}/course/bayesian_model_selection) | [Александр Адуенко]({{ site.baseurl }}/people/aduenko_aa), [Константин Яковлев]({{ site.baseurl }}/people/yakovlev_kd) | Дифференцированный зачет | 1 | +| 16:10-17:40 | [Математические методы прогнозирования]({{ site.baseurl }}/course/forecasting_methods) | [Денис Тихонов]({{ site.baseurl }}/people/tikhonov_dm), [Святослав Панченко]({{ site.baseurl }}/people/panchenko_sk) | Дифференцированный зачет | 1 | + +#### 5 курс, 9 семестр (вторник) + +| Время | Дисциплина | Преподаватели | Форма итоговой аттестации | Зачетные единицы | +| ----------- | -------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- | ------------------------- | ---------------- | +| 14:30-16:00 | [Байесовское мультимоделирование]({{ site.baseurl }}/course/bayesian_multimodeling) | [Олег Бахтеев]({{ site.baseurl }}/people/bakhteev_oy) | Дифференцированный зачет | 2 | +| 16:10-17:40 | [Создание интеллектуальных систем]({{ site.baseurl }}/course/rnd_in_ai) | [Андрей Грабовой]({{ site.baseurl }}/people/grabovoy_av) | Дифференцированный зачет | 2 | +| 18:00-19:30 | [Порождающие модели машинного обучения: Лекция]({{ site.baseurl }}/course/deep_generative_models) | [Роман Исаченко]({{ site.baseurl }}/people/isachenko_rv), [Матвей Морозов]({{ site.baseurl }}/people/morozov_ma) | Экзамен | 3 | +| 19:30-21:00 | [Порождающие модели машинного обучения: Семинар]({{ site.baseurl }}/course/deep_generative_models) | [Роман Исаченко]({{ site.baseurl }}/people/isachenko_rv), [Матвей Морозов]({{ site.baseurl }}/people/morozov_ma) | | | + +#### 6 курс, 11 семестр (четверг) + +| Время | Дисциплина | Преподаватели | Форма итоговой аттестации | Зачетные единицы | +| ----------- | ----------------------------------------------------------------------------------------- | ------------------------------------------------------------- | ------------------------- | ---------------- | +| 10:30-12:00 | [Функциональный анализ данных]({{ site.baseurl }}/course/functional_data_analysis) | [Вадим Стрижов]({{ site.baseurl }}/people/strijov_vv) | Экзамен | 3 | +| 12:10-13:40 | [Интеллектуальный анализ данных]({{ site.baseurl }}/course/intellectual_data_analysis) | [Вадим Стрижов]({{ site.baseurl }}/people/strijov_vv) | Зачет | 2 | +| 14:30-16:00 | [Вероятностные тематические модели]({{ site.baseurl }}/course/probabilistic_topic_models) | [Константин Воронцов]({{ site.baseurl }}/people/vorontsov_kv) | Дифференцированный зачет | 2 | + +
+ +### Весна 2025 + +#### Важные даты + +- **6 февраля:** Начало занятий на кафедре +- **9 февраля:** Крайний срок подачи заявок на [стипендию]({{ site.baseurl }}/materials/scholarship) +- **4 марта:** Понедельник 18:30 презентация о кафедре для студентов второго курса, оффлайн +- **10 марта:** Крайний срок подачи заявок на конференцию МФТИ +- **4 апреля:** 13:00 конференция и обсуждение тезисов для студентов 4-го и 6-го курсов +- **18-24 мая:** Экзаменационная неделя для студентов 3-го-6-го курсов +- **13 мая:** 17:00 (суббота) Зачет по научной работе для студентов 3-го-6-го курсов и аспирантов +- **2 июня:** Квалификационный экзамен для аспирантов +- **6 июня:** 10:00 предзащита для студентов 6-го курса +- **13 июня:** Государственная итоговая аттестация для выпускников аспирантуры +- **13 июня:** 10:00 предзащита для студентов 4-го курса +- **17 июня:** 13:00 (среда) защита для студентов 6-го курса, оффлайн ВЦ 355 +- **17 июня:** Научный доклад для выпускников аспирантуры +- **24 июня:** 13:00 (среда) защита для студентов 4-го курса, оффлайн ВЦ 355 + +#### 3 курс, 6 семестр (четверг) + +| Время | Дисциплина | Преподаватели | Форма итоговой аттестации | Зачетные единицы | +| ----------- | --------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------- | ---------------- | +| 12:10-13:40 | [Введение в машинное обучение]({{ site.baseurl }}/course/introduction_machine_learning) | [Андрей Грабовой]({{ site.baseurl }}/people/grabovoy_av), [Константин Воронцов]({{ site.baseurl }}/people/vorontsov_kv) | Дифференцированный зачет | 1 | +| 14:30-16:00 | [Практикум по программированию на Python](https://github.com/MelLain/mipt-python) | [Мурат Апишев]({{ site.baseurl }}/people/apishev_ma) | Зачет | 1 | +| 16:10-17:40 | [Создание интеллектуальных систем]({{ site.baseurl }}/course/rnd_in_ai) | [Андрей Грабовой]({{ site.baseurl }}/people/grabovoy_av), [Вадим Стрижов]({{ site.baseurl }}/people/strijov_vv) | Зачет | 1 | +| 17:50-19:20 | [Автоматизация научных исследований](http://m1p.org) | [Андрей Грабовой]({{ site.baseurl }}/people/grabovoy_av), [Олег Бахтеев]({{ site.baseurl }}/people/bakhteev_oy), [Вадим Стрижов]({{ site.baseurl }}/people/strijov_vv) | Дифференцированный зачет | 1 | + +#### 4 курс, 8 семестр (вторник) + +| Время | Дисциплина | Преподаватели | Форма итоговой аттестации | Зачетные единицы | +| ----------- | -------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | ------------------------- | ---------------- | +| 10:30-12:00 | [Рекомендательные системы]({{ site.baseurl }}/course/recommender_systems) | [Алексей Гришанов]({{ site.baseurl }}/people/grishanov_av), [Анна Володкевич]({{ site.baseurl }}/people/volodkevich_aa) | Дифференцированный зачет | 2 | +| 12:10-13:40 | [Математические методы прогнозирования]({{ site.baseurl }}/course/forecasting_methods) | [Денис Тихонов]({{ site.baseurl }}/people/tikhonov_dm), [Святослав Панченко]({{ site.baseurl }}/people/panchenko_sk) | Дифференцированный зачет | 3 | +| 14:30-16:00 | [Байесовский выбор моделей]({{ site.baseurl }}/course/bayesian_model_selection) | [Александр Адуенко]({{ site.baseurl }}/people/aduenko_aa), [Константин Яковлев]({{ site.baseurl }}/people/yakovlev_kd) | Экзамен | 2 | +| 16:10-17:40 | [Программная инженерия для анализа данных]({{ site.baseurl }}/course/software_engineering_data_analysis) | [Антон Хританков]({{ site.baseurl }}/people/khritankov_as) | Дифференцированный зачет | 1 | + +#### 5 курс, 10 семестр (вторник) + +| Время | Дисциплина | Преподаватели | Форма итоговой аттестации | Зачетные единицы | +| ----------- | -------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------- | ------------------------- | ---------------- | +| 12:10-13:40 | [Биоинформатика]({{ site.baseurl }}/course/bioinformatics) | [Иван Торшин]({{ site.baseurl }}/people/torshin_iy) | Дифференцированный зачет | 1 | +| 14:30-16:00 | [Создание интеллектуальных систем]({{ site.baseurl }}/course/rnd_in_ai) | [Андрей Грабовой]({{ site.baseurl }}/people/grabovoy_av) | Экзамен | 2 | +| 16:10-17:40 | [Программная инженерия для анализа данных]({{ site.baseurl }}/course/software_engineering_data_analysis) | [Антон Хританков]({{ site.baseurl }}/people/khritankov_as) | Дифференцированный зачет | 1 | +| 17:50-19:20 | [Байесовское мультимоделирование]({{ site.baseurl }}/course/bayesian_multimodeling) | [Олег Бахтеев]({{ site.baseurl }}/people/bakhteev_oy) | Экзамен | 2 | diff --git a/_i18n/ru/index.md b/_i18n/ru/index.md index 40f4cdea..8cd15ae7 100644 --- a/_i18n/ru/index.md +++ b/_i18n/ru/index.md @@ -1,17 +1,235 @@ -### [Расписание занятий](/ru/education/) +
+
+
+
+

Кафедра интеллектуальных систем

+

+ Мы готовим специалистов в области прикладной математики и физики — от бакалавриата до аспирантуры. Наши исследования охватывают теорию машинного обучения, интеллектуальные системы и практические приложения. Основываясь на базе ВЦ РАН, мы объединяем академическое превосходство и сотрудничество с индустрией. +

+
+ {% if site.github %} + + {% endif %} + {% if site.mail %} + + {% endif %} + {% if site.telegram %} + + {% endif %} + {% if site.youtube %} + + {% endif %} +
+
+
-[Кафедра интеллектуальных систем](/ru/about/) выпускает бакалавров и магистров по направлению «Прикладные математика и физика». + +
+

Новости

+
+
+
+ {% if site.posts and site.posts.size > 0 %} + {% assign news_sorted = site.posts | where: "lang", "ru" | sort: 'date' | reverse %} + {% for post in news_sorted limit:10 %} + +
+ {% if post.important %} + ВАЖНОЕ + {% endif %} +
+

{{ post.title }}

+

{{ post.date | date: "%d.%m.%Y" }}

+

{{ post.excerpt }}

+ + {% endfor %} + {% else %} + Нет новостей + {% endif %} +
+
+
+
-### Объявления и информация -- [Поступление на кафедру](/ru/admission/) -- [Слушателям отдельных курсов](/ru/admission/) -- [Учебные курсы](/ru/course/) и [преподаватели](/ru/people/) -- [Научные и учебные проекты](https://m1p.org) -- **Телеграм** [студентов](https://t.me/IS_MIPT) и [аспирантов](https://t.me/+BpMhAW-gWlM5OThi) -- **Youtube** [Machine learning – Intelligent Systems](https://www.youtube.com/@MachineLearningIS) -- **Rutube** [Machine learning – Intelligent Systems](https://rutube.ru/channel/40144363) + +
+

О кафедре

+
+

Кафедра интеллектуальных систем в Физтехе (МФТИ) является ведущим центром образования и исследований в области прикладной математики, науки о данных и искусственного интеллекта. Кафедра предлагает программы бакалавриата и магистратуры по направлению «Прикладная математика и физика» со специализациями в области науки о данных, проектирования интеллектуальных систем и машинного обучения.

+

Кафедра была основана академиком Константином Владимировичем Рудаковым и развивалась в рамках научной школы академика Юрия Ивановича Журавлева. Она базируется в Вычислительном центре Российской академии наук. В нашем составе — известные профессора, молодые ученые и эксперты из индустрии, средний возраст которых составляет 35 лет.

+

Исследования кафедры охватывают машинное обучение, многомерную статистику, глубокое обучение, выбор моделей, генеративные нейронные сети и анализ сложных данных. Прикладные проекты включают анализ текста и изображений, обработку биомедицинских сигналов и интерфейсы «мозг-компьютер». Кафедра активно сотрудничает с международными университетами, научными центрами и высокотехнологичными компаниями, предлагая студентам уникальные возможности для стажировок, двойных дипломов и совместных исследований.

+

Мы ценим открытость, инновации и постоянное совершенствование, поддерживая студентов стипендиями и личным наставничеством. Присоединяйтесь к нам, чтобы учиться, исследовать и внедрять инновации в области интеллектуальных систем!

+
+
-**Занятия:** -- бакалавры [m1p.org/go_zoom](https://m1p.org/go_zoom) -- магистры [m1p.org/go_zoom2](https://m1p.org/go_zoom2) + +
+
+
+

2003

+

год основания кафедры

+
+
+

>50%

+

выпускников защитили кандидатские диссертации

+
+
+

<35

+

средний возраст преподавателей курсов

+
+
+

170+

+

open source проектов на GitHub

+
+
+

каждый
семестр

+

студенты представляют научные отчеты: paper-code-presentation

+
+
+

NeurIPS,
ICML, ICLR,
AISTATS

+

top-tier конференции публикуют наши исследования

+
+
+
+ +
+

Личности

+

+ Мы гордимся нашими основателями и преподавателями, которые внесли значительный вклад в область машинного обучения. Их работа проложила путь к современным достижениям в области искусственного интеллекта. +

+ {% assign featured_people = "zhuravlyov_yv,rudakov_kv,vorontsov_kv,strijov_vv" | split: "," %} +
+ {% for person_id in featured_people %} + {% for profile in site.people %} + {% assign profile_id = profile.id | split: "/" | last %} + {% if profile_id == person_id %} +
+

+ {% if profile.avatar %} + + {% else %} + + {% endif %} + {% t people.{{ profile_id }} %} +

+
+ {% endif %} + {% endfor %} + {% endfor %} +
+
+ + +
+

Курсы

+

+ Мы предлагаем широкий спектр курсов по прикладной математике, анализу данных и машинному обучению как для студентов бакалавриата, так и для магистрантов. Наша учебная программа разработана для обеспечения прочной теоретической базы наряду с практическими навыками, необходимыми в индустрии. +

+ {% for type in site.global.course.types %} + {% if type == 'bachelor' or type == 'master' %} +
+

{% t site.global.course.types.{{ type }} %}

+
+
+ {% for course in site.course %} + {% if course.type contains type %} + +
+

+ {% t courses.{{ course.id | split: "/" | last }} %} +

+
+ + {% endif %} + {% endfor %} +
+ {% endif %} + {% endfor %} +
+ + +
+ +
+ + +
+

Научная работа

+
+

+ Мы открыто публикуем результаты исследований и приглашаем к сотрудничеству студентов, исследователей и промышленные компании. +

+
+
+ Научные исследования +

+ Наша кафедра проводит фундаментальные и прикладные исследования в области машинного обучения, анализа данных, искусственного интеллекта и смежных областей. + Результаты публикуются в открытом доступе и представляются на международных конференциях. Мы приветствуем совместные проекты и новые идеи! +

+

+ Научные направления: распознавание образов, обработка естественного языка, биомедицинские сигналы, генеративные модели, теория машинного обучения +

+
+
+ Дипломные работы +

+ Студенты участвуют в реальных исследованиях, готовят дипломные работы и публикуют свои результаты. + Мы поддерживаем открытое опубликование кода и статей и приглашаем всех к сотрудничеству по темам дипломных работ и исследовательским проектам. +

+

+ Работа студентов: публикации, дипломные работы бакалавров и магистров, кандидатские диссертации +

+
+
+ Стипендии +

+ Мы поддерживаем исследования наших студентов, присуждая несколько стипендий каждый семестр. + Научная стипендия имени К.В. Рудакова присуждается студентам бакалавриата и магистратуры за академические и исследовательские достижения. + Спонсор: Forecsys Group. +

+
+
+
Стажировки
+

+ С самого начала кафедра активно сотрудничает с базовыми организациями группы компаний Forecsys и участвует в совместных проектах с ведущими технологическими компаниями. +

+
+

Форексис

+

Антиплагиат

+

Яндекс

+

СБЕР

+
+
+
+
+
+ + +
+

Наша жизнь

+

+ Здесь мы делимся некоторыми моментами из жизни нашей кафедры: учебные мероприятия, защиты дипломов, встречи выпускников. +

+ +
diff --git a/_i18n/ru/paper_guidelines.md b/_i18n/ru/paper_guidelines.md index 981f33ec..9a89d07a 100644 --- a/_i18n/ru/paper_guidelines.md +++ b/_i18n/ru/paper_guidelines.md @@ -1,31 +1,44 @@ -# Шаблоны -* [Шаблон слайдов доклада бакалавра и магистра](http://www.machinelearning.ru/wiki/images/3/38/Surname2021TitleSlides.zip) - -# Стандарты -* [Положение о защите ВКР МФТИ](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vypusknoy_kvalikafitsionnoy_rabote_studentov_mfti_49_1_ot_21_01) -* [Положение о присуждении ученой степени](http://www.consultant.ru/document/cons_doc_LAW_152458/3accc895434fd7ce6fd7d8f8a570ab064e960560/) - -# Рекомендации -* [ML-wiki: рекомендации по написанию](http://www.machinelearning.ru/wiki/index.php?title=%D0%9D%D0%B0%D0%BF%D0%B8%D1%81%D0%B0%D0%BD%D0%B8%D0%B5_%D0%BE%D1%82%D1%87%D1%91%D1%82%D0%BE%D0%B2_%D0%B8_%D1%81%D1%82%D0%B0%D1%82%D0%B5%D0%B9_%28%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%86%D0%B8%D0%B8%29) -* [ML-wiki: подача в русский журнал](http://www.machinelearning.ru/wiki/index.php?title=%D0%90%D0%B2%D1%82%D0%BE%D0%BC%D0%B0%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%B8_%D1%81%D1%82%D0%B0%D0%BD%D0%B4%D0%B0%D1%80%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%BD%D0%B0%D1%83%D1%87%D0%BD%D1%8B%D1%85_%D0%B8%D1%81%D1%81%D0%BB%D0%B5%D0%B4%D0%BE%D0%B2%D0%B0%D0%BD%D0%B8%D0%B9_%28%D0%BF%D1%80%D0%B0%D0%BA%D1%82%D0%B8%D0%BA%D0%B0%2C_%D0%92.%D0%92._%D0%A1%D1%82%D1%80%D0%B8%D0%B6%D0%BE%D0%B2%29#.D0.9A.D0.B0.D0.BA_.D0.BF.D0.BE.D0.B4.D0.B0.D1.82.D1.8C_.D1.81.D1.82.D0.B0.D1.82.D1.8C.D1.8E_.D0.B2_.D1.80.D1.83.D1.81.D1.81.D0.BA.D0.B8.D0.B9_.D0.B6.D1.83.D1.80.D0.BD.D0.B0.D0.BB) -* [ML-wiki: подача в международный журнал](http://www.machinelearning.ru/wiki/index.php?title=%D0%90%D0%B2%D1%82%D0%BE%D0%BC%D0%B0%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%B8_%D1%81%D1%82%D0%B0%D0%BD%D0%B4%D0%B0%D1%80%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D1%8F_%D0%BD%D0%B0%D1%83%D1%87%D0%BD%D1%8B%D1%85_%D0%B8%D1%81%D1%81%D0%BB%D0%B5%D0%B4%D0%BE%D0%B2%D0%B0%D0%BD%D0%B8%D0%B9_%28%D0%BF%D1%80%D0%B0%D0%BA%D1%82%D0%B8%D0%BA%D0%B0%2C_%D0%92.%D0%92._%D0%A1%D1%82%D1%80%D0%B8%D0%B6%D0%BE%D0%B2%29#.D0.9A.D0.B0.D0.BA_.D0.BF.D0.BE.D0.B4.D0.B0.D1.82.D1.8C_.D1.81.D1.82.D0.B0.D1.82.D1.8C.D1.8E_.D0.B2_.D0.BC.D0.B5.D0.B6.D0.B4.D1.83.D0.BD.D0.B0.D1.80.D0.BE.D0.B4.D0.BD.D1.8B.D0.B9_.D0.B6.D1.83.D1.80.D0.BD.D0.B0.D0.BB) -* [Курс "моя первая научная статья"](../../course/automation_scientific_research/index.html) -* [Инструкция как защитить диссертацию (актуальна на март 2022)](https://docs.google.com/document/d/1TzV5e7-7WhPwLzgyWidYykx2HlXYs0g4pBrr28dpbrk/edit?usp=sharing) - -# Куда подать статью -* [SJR индекс журналов](https://www.scimagojr.com/) -* [ex-Guide2Research: список конференций и журналов со статистикой](https://research.com/) -* [Ранги международных конференций](http://www.conferenceranks.com/) -* [Основные конференции и воркшопы по ML (обновляется раз в месяц)](https://tinyurl.com/bahleg-conf) -* [Основные журналы по ML (обновляется раз в полгода)](https://tinyurl.com/bahleg-journals) - -# Объем и содержание ВКР -Рекомендованный объем – пожалуйста, прочтите Положение о ВКР https://intsystems.github.io/ru/materials/paper_guidelines/ Необходимого объема не определено. +## Написание статей и защита ВКР + +На этой странице вы найдете рекомендации по написанию научных статей, выбору места публикации и защите вашей дипломной работы на кафедре Интеллектуальных систем. + +### Рекомендации и гайдлайны по написанию научной работы + +- [Курс "Моя первая научная статья" (m1p)](<[../../course/automation_scientific_research/index.html](https://m1p.org/index.php/My_first_scientific_paper)>) +- [Написание отчётов и статей для студентов и аспирантов](http://www.machinelearning.ru/wiki/index.php?title=%D0%9D%D0%B0%D0%BF%D0%B8%D1%81%D0%B0%D0%BD%D0%B8%D0%B5_%D0%BE%D1%82%D1%87%D1%91%D1%82%D0%BE%D0%B2_%D0%B8_%D1%81%D1%82%D0%B0%D1%82%D0%B5%D0%B9_%28%D1%80%D0%B5%D0%BA%D0%BE%D0%BC%D0%B5%D0%BD%D0%B4%D0%B0%D1%86%D0%B8%D0%B8%29) +- [Рекомендации от ICML для статей по ML](https://icml.cc/Conferences/2002/craft.html) +- [Рекомендации от Nature для любого типа статей](https://www.nature.com/scitable/topicpage/scientific-papers-13815490/#) + +### Выбор места публикации и процесс подачи + +- [Куда и как подавать свою работу от m1p](https://m1p.org/index.php/Week_10) +- [SJR индекс журналов](https://www.scimagojr.com/) +- [Ранги международных конференций](http://www.conferenceranks.com/) +- [Основные конференции и воркшопы по ML (обновляется раз в месяц)](https://tinyurl.com/bahleg-conf) +- [Основные журналы по ML (обновляется раз в полгода)](https://tinyurl.com/bahleg-journals) + +### О защите дипломных работ на кафедре + +#### Чеклист на (пред)защиту + +1. Дипломная работа, слайды, код находятся в вашем репозитории _под орагнизацией_ [_кафедры_](https://github.com/intsystems/) +2. Ссылка на вашу работу находится в [таблице дипломных работ]({{ site.baseurl }}/materials/thesis) + +#### Документы на защиту + +1. Отзыв научного руководителя +2. Справка антиплагиата +3. Рецензия внешнего рецензента (для магистров) + +#### Объем и содержание ВКР + +О рекомендумом объеме, пожалуйста, прочтите в [положение о защите ВКР в МФТИ](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vypusknoy_kvalikafitsionnoy_rabote_studentov_mfti_49_1_ot_21_01). Необходимого объема не определено. Важны ваши результаты, выносимые на защиту. Они должны быть оформлены в виде научной статьи (двух для магистров). Публикация этих статей в рецензируемом журнале означает принятие ваших результатов научным сообществом. Вместе с формальным введением они и составят рекомендованный объем. При изложении -1. Опишите условия и ваши предположения относительно решаемой задачи: пространства, алгебраические структуры, статистические гипотезы. + +1. Опишите условия и ваши предположения относительно решаемой задачи: пространства, алгебраические структуры, статистические гипотезы. 2. Обоснуйте решение задачи, укажите свойства решения. 3. Сформулируйте ваши результаты в виде строгих утверждений. 4. Проанализируйте полученное решение и результаты. @@ -33,37 +46,31 @@ Избегайте описывать ваше решение в стиле “как я это делаю шаг за шагом”. Важнее описать “зачем я это делаю” и “какой вклад это вносит в решение задачи”. Не нужны -1) копипаста схем и иллюстраций из других статей, -2) автоматически сгенерированный текст. + +1. Копирование схем и иллюстраций из других статей. +2. Автоматически сгенерированный текст. Чужой материал и материал соавторов + 1. Подавайте со ссылками, ровно в том объеме, в каком это требуется для пояснения ваших личных результатов. 2. Перерабатывайте и улучшайте чужой текст и диаграммы. -# Защита дипломных работ -## Документы на предзащиту -1. Дипломная работа, слайды, код – загрузить [в репозиторий](https://github.com/intsystems/) и поставить [ссылку в таблицу](https://intsystems.github.io/ru/materials/thesis/) -2. Проследите, чтобы сам репозиторий был в огранизации /intsystems/ -## Документы на защиту -1. Отзыв научрука -2. Справка антиплагиата -3. Рецензия внешнего рецензента (для магистров) +#### FAQ по защите -## FAQ по защите 1. Можно ли править текст диплома после предзащиты? – Можно и нужно, и даже после защиты. Результаты диплома будут использованы презде всего вами. Но если на предзащите представлена версия, которая требует существенной правки, это поднимает вопрос о качестве работы и об оценке. 2. Где можно найти формальные требования к ВКР? – Обязательно прочтите [Положения о защите](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vkr) 3. Во сколько предзащита и защита? – Предзащиты в 10:00, защиты в 13:00. -4. Онлайн или оффлайн? – Предзащиты онлайн, защиты оффлайн ул. Вавилова, 42, каб. 355. Пропускной режим по спискам, уточняйте это отдельно. -5. Нужно ли печатать ВКР на защиту? – Да. Это вежливо по отношению к комиссии, дать почитать бумажный вариант текста дипломной работы. +4. Онлайн или оффлайн? – Предзащиты онлайн, защиты оффлайн ул. Вавилова, 42, каб. 355. Пропускной режим по спискам, уточняйте это отдельно. +5. Нужно ли печатать ВКР на защиту? – Да. Это вежливо по отношению к комиссии, дать почитать бумажный вариант текста дипломной работы. 6. Какой формат защиты? – Доклад на 7 минут + 5 минут на вопросы. Следите за временем! -7. Когда нужно загрузить ВКР? – Кафедра не знает, когда вам нужно загрузить ВКР в личный кабинет. Но вы должны к предзащите загрузить диплом и все остальные ссылки на [страницу кафедры](https://intsystems.github.io/materials/thesis/) -8. Когда нужен отзыв научника? К защите. Приносите его с собой. Магистры – с резензентом то же. +7. Когда нужно загрузить ВКР? – Кафедра не знает, когда вам нужно загрузить ВКР в личный кабинет. Но вы должны к предзащите загрузить диплом и все остальные ссылки на [страницу кафедры]({{ site.baseurl }}/materials/thesis) +8. Когда нужен отзыв научника? К защите. Приносите его с собой. Магистры – с резензентом то же. 9. Когда нужен отчёт антиплагиата? – К защите. Приносите его с собой. В случае высокого процента заимствований на отчете должна быть подпись научного руководителя. 10. Нужен ли отзыв рецензента? – Для бакалавров нет, для магистров да. 11. Когда нужно загрузить отзыв рецензента? – К защите. Приносите его с собой (если рецензент не с физтеха, то нужно заверение его подписи с места работы). 12. Какие требования к рецензенту? – См. пункт 5 положений. 13. Достаточно ли сканов документов? – Нет, нужны оригиналы. -16. Нужно ли мне все бумаги загружать в личный кабинет мфти? – Только текст дипломной работы с русскоязычной аннотацией. +14. Нужно ли мне все бумаги загружать в личный кабинет мфти? – Только текст дипломной работы с русскоязычной аннотацией. - загружаете текст в ЛК > Учебный процесс > Загрузка ВКР, - проверяете на Антиплагиате, - так как ваша работа ранее опубликована вами же, Антиплагиат должен ее найти (и это прекрасно, так как говорит о том, что научное сообщество с ней знакомо), @@ -71,31 +78,40 @@ - по этой же причине не добавляйте в диплом сгенерированных текстов (ни к чему это – у нас нет требований к объему, но зато есть требования к качеству работы), - после этого загрузите русскоязычную аннотацию и текст работы в ЭБС (кнопка ниже), - важно это сделать позднее чем за два дня до защиты (если защита 25, загрузите 22). -17. Язык текста – мы не нашли в Положении о защите ВКР требований к языку. Поэтому, с учетом того что ваша работа опубликована журнале, оставляем решение за вами. +15. Язык текста – мы не нашли в Положении о защите ВКР требований к языку. Поэтому, с учетом того что ваша работа опубликована журнале, оставляем решение за вами. + +#### Стандарты + +- [Положение о защите ВКР МФТИ](https://mipt.ru/docs/download.php?code=prikaz_ob_utverzhdenii_polozheniya_o_vypusknoy_kvalikafitsionnoy_rabote_studentov_mfti_49_1_ot_21_01) +- [Положение о присуждении ученой степени в РФ](http://www.consultant.ru/document/cons_doc_LAW_152458/3accc895434fd7ce6fd7d8f8a570ab064e960560/) -# Функция Кафедры интеллектуальных систем + diff --git a/_i18n/ru/scholarship.md b/_i18n/ru/scholarship.md index 09fe14e4..01f28591 100644 --- a/_i18n/ru/scholarship.md +++ b/_i18n/ru/scholarship.md @@ -1,21 +1,24 @@ ## Научная академическая стипендия им. К.В. Рудакова -Стипендия поощряет студентов 2–4 курса бакалавриата и 1–2 курса магистратуры Кафедры интеллектуального анализа данных, ведущих научные-исследования в области прикладной математики: машинного обучения, анализа данных, и других разделов математики. Стипендия выплачивается ежемесячно. +Стипендия поощряет студентов 2–4 курса бакалавриата и 1–2 курса магистратуры Кафедры интеллектуального анализа данных, ведущих научные-исследования в области прикладной математики: машинного обучения, анализа данных, и других разделов математики. Стипендия выплачивается ежемесячно. ### Критерии для отбора стипендиатов -* Вероятность своевременного выполнения научной работы высокого качества. -* Ожидаемый вклад в исследуемую проблему или решение задачи. -* Успехи в преподавании и развитии Кафедры. + +- Вероятность своевременного выполнения научной работы высокого качества. +- Ожидаемый вклад в исследуемую проблему или решение задачи. +- Успехи в преподавании и развитии Кафедры. ### Прием заявок на стипендию -* Дедлайн осень 2: сентября -* Дедлайн весна 3: февраля -* Заявку загрузить [сюда, в Google form](https://forms.gle/4TQrMp4mWPV8CxcE9) -* [Заявки прошлых лет и Порядок назначения стипендии](/images/NIR_KV_Rudakov_scholarship.pdf) +- Дедлайн осень: 2 сентября +- Дедлайн весна: 3 февраля +- Заявку загрузить [сюда, в Google form](https://forms.gle/4TQrMp4mWPV8CxcE9) +- [Заявки прошлых лет и Порядок назначения стипендии](images/NIR_KV_Rudakov_scholarship.pdf) ### Состав комиссии + Представители компаний [«Антиплагиат»](https://antiplagiat.ru/), [«ПроКомплаенс»](https://www.forecsys.ru/%D0%BE-%D0%BA%D0%BE%D0%BC%D0%BF%D0%B0%D0%BD%D0%B8%D0%B8/), и [«Форексис»](https://forecsys.ru/) ### Шаблон заявки -ФИО студента, Средний балл в ЛК, ФИО и ученая ступень научного руководителя, Тема научной работы, Аннотация, Ожидаемый результат (желательно указать фактический результат и формальный – журнал где планируется публикация, или другой вид представления результата), Преподавание и в развитие Кафедры ИС, участие и планы, Ссылка на дополнительные материалы (если есть; например, задел по научной работе или результаты прошлого семестра) + +ФИО студента, Средний балл в ЛК, ФИО и ученая ступень научного руководителя, Тема научной работы, Аннотация, Ожидаемый результат (желательно указать фактический результат и формальный – журнал где планируется публикация, или другой вид представления результата), Преподавание и в развитие Кафедры ИС, участие и планы, Ссылка на дополнительные материалы (если есть; например, задел по научной работе или результаты прошлого семестра) diff --git a/_i18n/ru/seminars.md b/_i18n/ru/seminars.md deleted file mode 100644 index 2b6162bc..00000000 --- a/_i18n/ru/seminars.md +++ /dev/null @@ -1,221 +0,0 @@ -# Встречи и семинары - -### Семинар В. В. Стрижова, Научная статья за семестр. Риски и результаты в машинном обучении - - - -### Встреча с Никитой Животовским, выпускником Кафедры интеллектуальных систем МФТИ, 2013 - -**Дата:** 21.04.2022 - -**Гость:** [Никита Животовский](https://www.linkedin.com/in/nikita-zhivotovskiy-06816597/) --- канд. физ.-мат. наук., выпускник кафедры 2013, исследователь Google Research, Zürich. - - -
-
- -### Встреча с Кириллом Павловым, выпускником Кафедры интеллектуальных систем МФТИ, 2012 - -**Дата:** 27.03.2022 - -**Гость:** [Кирилл Павлов](https://www.linkedin.com/in/pavlov99/) --- выпускник кафедры 2012, исследователь. - - -
-
- -### Встреча с Романом Сологубом, выпускником Кафедры интеллектуальных систем МФТИ, 2010 - -**Дата:** 11.03.2022 - -**Гость:** [Роман Сологуб](https://www.linkedin.com/in/roman-sologub-phd-86038648/) - -Роман --- канд. физ.-мат. наук., выпускник кафедры 2010, финансовый аналитик из Лондона. - - - -
-
- -### Встреча с выпускниками Кафедры интеллектуальных систем МФТИ, 2013 - -**Дата:** 17.02.2022 - -**Гости:** [Михаил Кузнецов](https://scholar.google.com/citations?user=w1CmemUAAAAJ&hl=ru&oi=ao), [Никита Ивкин](https://scholar.google.com/citations?user=wHAYz5wAAAAJ&hl=ru&oi=ao) - -Выпускники кафедры занимаются исследованиями в области машинного обучения и анализа данных в крупных коммерческих компаниях. - -* Михаил Кузнецов – канд. физ.-мат. наук. МФТИ, сотрудник Yahoo и Amazon -* Никита Ивкин – PhD Johns Hopkins University, сотрудник Amazon - - -
-
- -### Априорное распределение параметров в задачах выбора моделей глубокого обучения - -**Дата:** 24.01.2022 - -**Докладчик:** [Андрей Грабовой](../../people/grabovoy_av) - -Семинар посвящен дистилляции моделей глубокого обучения. Обсуждается выравнивание структур моделей учителя и ученика. Для оптимизации параметров ученика используется байесовский вывод. В качестве примеров учителя и ученика приводятся полносвязные и рекуррентные нейросети. - - - -
-
- -### Снижение размерности пространства в задачах декодирования сигналов - -**Дата:** 13.12.2021 - -**Докладчик:** [Роман Исаченко](../../people/isachenko_rv) - -Доклад посвящен проблеме снижения размерности пространства при решении задачи декодирования сигналов. Процесс декодирования заключается в восстановлении зависимости между двумя гетерогенными наборами данных. Особенностью рассматриваемой задачи является наличие скрытых зависимостей не только в исходных сигналах, но и в целевых. Предлагаются методы снижения размерности, позволяющие учитывать зависимости в исходном и целевом пространствах. - - - - -
-
- -### Uncertainty, Out-of-distribution detection for NNs - -**Дата:** 8.07.2021 - -**Докладчик:** [Максим Панов](https://faculty.skoltech.ru/people/maximpanov) - -Максим Панов (доцент Сколтеха) расскажет на семинаре что такое Uncertainty в байесовском выводе. - - - - -# Защиты диссертаций - -### Роман Исаченко, Снижение размерности пространства в задачах декодирования сигналов, 2021 - -*Исследуется задача выбора модели при восстановлении скрытых зависимостей в исходном и в целевом пространствах. Целевая переменная – вектор, компоненты которого являются зависимыми. Гетерогенные пространства исходных и целевых переменных обладают существенно избыточной размерностью. Требуется построить модель, адекватно описывающую исходное и целевое пространства при наблюдаемой мультикорреляции в обоих пространствах. Предлагается снизить размерность путём проецирования исходных и целевых переменных в скрытое пространство. Предлагаются линейные и нелинейные методы согласования прогностических моделей в пространствах высокой размерности.* - - - -[Ссылка на диссертацию](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/31-isachenko/ds05_31-isachenko_main.pdf?18) -
-
-### Олег Бахтеев, Байесовский выбор модели глубокого обучения, 2020 - -*В работе рассматривается задача автоматического построения моделей глубокого обучения оптимальной и субоптимальной сложности. Под сложностью модели понимается минимальная длина описания, т.е. минимальное количество информации, которое требуется для передачи информации о модели и о выборке. Вычисление минимальной длины описания модели является вычислительно сложной процедурой. В работе предлагается получение ее приближенной оценки, основанной на связи минимальной длины описания и обоснованности модели. Для получения оценки обоснованности используются вариационные методы получения оценки обоснованности, основанные на аппроксимации неизвестного апостериорного распределения другим заданным распределением. Под субоптимальной сложностью понимается вариационная оценка обоснованности модели. Одна из проблем построения моделей глубокого обучения — большое количество параметров моделей. Поэтому задача выбора моделей глубокого обучения включает в себя выбор стратегии построения модели, эффективной по вычислительным ресурсам.* - - - -[Ссылка на диссертацию](https://frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/26-bahteev/ds05-26-bahteev_main.pdf?28) -
-
- -### Анастасия Мотренко, Выбор моделей прогнозирования, 2019 - -*Цель работы: исследование свойств и разработка новых методов выбора модели в условиях избыточного мультикоррелирующего признакового пространства. -Проблема: при решении задачи декодирования временных рядов признаковое описание обладает корреляцией сложной мультииндексной структуры. -Избыточность признакового пространства, мультикорреляция и высокая размерность приводят к завышению сложности модели и получению неустойчивых оценок параметров. -Предложен метод выбора признаков, учитывающий многоиндексное мультикоррелирующее представление данных. Метод основан на решении задачи квадратичного программирования.* - - - - -[Ссылка на диссертацию](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/23-motrenko/ds05_23-motrenko_main.pdf?683) -
-
- -### Александр Адуенко, Выбор мультимоделей в задачах классификации, 2017 - -*Мультимодели используются в случае отвержения гипотезы о простоте выборки. В случае, когда важность признаков зависит от их значений, одиночная обобщенно-линейная модель не позволяет это учесть. -Мультимодели являются интерпретируемым обобщением случая одиночной модели. Они могут содержать большое число близких моделей, что ведет к низкому качеству прогноза и потере интерпретируемости. Для решения этой проблемы предложен статистический подход к сравнению моделей и основанные на нем методы прореживания мультимоделей, позволяющие получить адекватную мультимодель, содержащую попарно статистически различимые модели.* - - - -[Ссылка на диссертацию](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/11-aduenko/11-Aduenko_main.pdf?626) -
-
-### Арсентий Кузьмин, Иерархическая классификация коллекций документов, 2017 - -*Работа посвящена разработке моделей классификации коллекций документов. Коллекция имеет иерархическую структуру, заданную экспертами. Требуется построить ранжирующую модель, которая учитывает описания документов, экспертную кластеризацию и возвращает ранжированный список релевантных тем. Предлагается метрическая вероятностная модель ранжирования тематических кластеров. Используются вариационные методы оценки вероятности принадлежности документа кластеру.* - - - -[Ссылка на диссертацию](https://www.frccsc.ru/sites/default/files/docs/ds/002-073-05/diss/08-kuzmin/008-kuzmin_main-txt.pdf?809) -
-
- -# Защиты бакалавров и магистров -### Предзащита бакалавров, 2025 - -**Студенты**: Егор Задворнов, Сергей Фирсов, Илья Степанов, Алексей Ребриков, Фанис Хафизов, Денис Рубцов, Иван Папай, Мухаммадшариф Набиев, Алтай Эйнуллаев, Федор Соболевский, Вадим Касюк, Владислав Мешков, Анастасия Линич, Глеб Карпеев - - - -
-
- -### Предзащита магистров, 2025 - -**Студенты**: Никита Корнилов, Галина Боева, Эдуард Владимиров, Арина Чумаченко, Герман Грицай, Ксения Петрушина, Ильдар Хабутдинов, Марат Хусаинов - - - -
-
- -### Предзащита бакалавров, 2024 - -**Студенты**: Бабкин Пётр, Богданов Александр, Веприков Андрей, Дорин Даниил, Игнашин Игорь, Киселев Никита, Крейнин Матвей, Никитина Мария, Охотников Никита, Семкин Кирилл, Терентьев Александр, Вознюк Анастасия, Ремизова Анна - - - - -
-
- -### Предзащита магистров, 2024 - -**Студенты**: Константин Яковлев, Полина Барабанщикова, Роман Клыпа, Григорий Ксенофонтов, Эмиль Алкин, Мария Ковалева, Александр Толмачев - - - -
-
- - - -### Защита бакалавров, 2022 - -**Студенты**: Константин Яковлев, Мария Горпинич, Антонина Курдюкова, Вячеслав Горчаков, Антон Пилькевич, Максим Христолюбов - - -
-
- -### Защита магистров, 2022 -**Студенты**: Петр Мокров, Наталия Вареник, Алексей Григорьев, Святослав Панченко, Павел Северилов, Денис Тихонов, Александр Колесов, Алексей Гришанов - - - -
-
- -### Защита бакалавров, 2021 -**Студенты**: Дмитрий Ковалев, Антон Бишук, Кирилл Вайсер, Ольга Гребенькова, Руслан Гунаев, Владимир Жолобов, Рустем Исламов, Виктор Панкратов, Николай Савельев, Андрей Филатов, Анастасия Филиппова, Александра Харь, Вячеслав Шокоров, Тагир Саттаров - - -
-
- - - -### Защита магистров, 2021 -**Студенты**: Егор Гладин, Андрей Грабовой, Егор Кириллов, Вадим Кислинский, Евгений Козлинский, Григорий Малиновский, Егор Шульгин, Василий Новицкий, Анна Рогозина, Никита Плетнев, Алина Самохина, Тамаз Гадаев, Глеб Моргачев - - -
-
- - - diff --git a/_includes/footer.html b/_includes/footer.html index 01daa564..55c5bacf 100644 --- a/_includes/footer.html +++ b/_includes/footer.html @@ -1,9 +1,36 @@
- -
- {% t site.index.department %}
- {% t site.index.address %}
- - © 2003- - Intelligent Systems. All rights reserved. -
\ No newline at end of file +
+
+ {% if site.github %} + + {% endif %} + {% if site.mail %} + + {% endif %} + {% if site.telegram %} + + {% endif %} + {% if site.youtube %} + + {% endif %} + {% if site.rutube %} + +
+ {% endif %} + {% t site.index.department %}, {% t site.index.address %} +
+ Ⓒ 2003 – + +
+
+ diff --git a/_includes/navbar.html b/_includes/navbar.html index 8ae91009..efc022f5 100644 --- a/_includes/navbar.html +++ b/_includes/navbar.html @@ -2,7 +2,20 @@
-
+ +
+ +
+ +
+ +
+
+ {% if site.github %} + + + + {% endif %} + {% if site.mail %} + + + + {% endif %} + {% if site.telegram %} + + + + {% endif %} + {% if site.youtube %} + + + + {% endif %} + {% if site.rutube %} + + Rutube + + {% endif %}
diff --git a/_includes/sidecar.html b/_includes/sidecar.html deleted file mode 100644 index 72304f38..00000000 --- a/_includes/sidecar.html +++ /dev/null @@ -1,71 +0,0 @@ -
-
- -
-
- {% t site.name %} -
- - - -

- {% for line in site.header %} - {{ line }}
- {% endfor %} -

- - - - {% for lang in site.languages %} - {% if lang == site.default_lang and site.default_locale_in_subfolder != true %} - {{ site.global.langs[lang] }} - {% else %} - {{ site.global.langs[lang] }} - {% endif %} - {% assign next = forloop.index | plus: 1 %} - - {% if forloop.last != true or site.languages[forloop.index] == site.lang and next < forloop.length %} - • - {% endif %} - {% endfor %} - - {% if page.edit == true %} - | - - {% endif %} - - - -
- {{ content | toc_only }} -
- -
- - {% if site.github %} - - {% endif %} - {% if site.mail %} - - {% endif %} - {% if site.telegram %} - - {% endif %} -
- {% if site.youtube %} - - {% endif %} - {% if site.rutube %} - - {% endif %} -
diff --git a/_includes/toc.html b/_includes/toc.html new file mode 100644 index 00000000..e4f53f10 --- /dev/null +++ b/_includes/toc.html @@ -0,0 +1,18 @@ +{% capture toc_title %}{% if page.toc_title %}{{ page.toc_title }}{% else %}{% t site.toc.title %}{% endif %}{% endcapture %} + diff --git a/_layouts/course.html b/_layouts/course.html index a15e059b..01b14d2a 100755 --- a/_layouts/course.html +++ b/_layouts/course.html @@ -2,51 +2,47 @@ layout: default --- {% if page.type == "bachelor" %} - + {% else %} - + {% endif %} - -
-

{% t courses.name.{{ page.id | split: "/" | last }} %}

+

+ {% t courses.{{ page.id | split: '/' | last }} %} +

- -{% if page.avatar %} - -{% endif %} - {% if page.site %} - {% t course.website %}
+ + + {% t course.website %} + +
{% endif %} -
- -{{ content }} - {% if page.lecturers %} -
-

{% t course.teachers %}

-
-
- {% assign lecturers = page.lecturers | split: "," %} - {% for lecturer in lecturers %} - {% for profile in site.people %} - {% if profile.url contains lecturer %} -
+ {% assign lecturers = page.lecturers | split: "," %} +{% for lecturer in lecturers %} +{% for profile in site.people %} +{% if profile.url contains lecturer %} +

- {% if profile.avatar %} - - {% else %} - - {% endif %} - {% t peoples.name.{{ profile.id | split: "/" | last }} %} + {% if profile.avatar %} + + + + {% else %} + + + + {% endif %} + {% t people.{{ profile.id | split: "/" | last }} %}

-
+
{% endif %} - {% endfor %} - {% endfor %} +{% endfor %} +{% endfor %}
-
{% endif %} + +{{ content }} diff --git a/_layouts/default.html b/_layouts/default.html index 124bb5a5..f12e00a2 100755 --- a/_layouts/default.html +++ b/_layouts/default.html @@ -1,82 +1,91 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - {% if page.title %}{% t page.title %}{% else %}{% t site.name %}{% endif %} - - - - - - - - - - - - - - - - - - - - - - - - - - - -
- {% include navbar.html %} -
-
- {% if site.sidebar %} - {% if site.image %} -
- {% else %} -
- {% endif %} - {% include sidecar.html %} -
-
- {{ content }} - {% include footer.html %} -
- {% else %} -
- {{ content }} - {% include footer.html %} -
- {% endif %} - -
- + + + + + + + + + + + + + + + + + + + {% if page.title %}{% t page.title %}{% else %}{% t site.name %}{% endif %} + + + + + + + + + + + + + + + + + + + + + + + + + + + + + {% if page.toc %} + {% include toc.html %} + {% endif %} +
+ {% include navbar.html %} +
+
+ {% if page.home or page.url == '/' or page.url == '/en/' or page.url == '/ru/' %} +
+ {{ content }} +
+ {% else %} +
+ {{ content }} +
+ {% endif %} +
+ {% include footer.html %} + {% if page.toc %} + + {% endif %} + diff --git a/_layouts/news.html b/_layouts/news.html new file mode 100644 index 00000000..3e563260 --- /dev/null +++ b/_layouts/news.html @@ -0,0 +1,12 @@ +--- +layout: default +--- +
+
+

{{ page.title }}

+

{{ page.date | date: "%B %d, %Y" }}

+
+
+ {{ content }} +
+
diff --git a/_layouts/page.html b/_layouts/page.html index 0c6eda15..34bf5ee4 100644 --- a/_layouts/page.html +++ b/_layouts/page.html @@ -1,14 +1,9 @@ --- layout: default --- -{% if page.image %} -
- -
-{% endif %} {% if site.lang == 'ru' %} - -{% else %} - + +{% else %} + {% endif %} {{ content }} diff --git a/_layouts/profile.html b/_layouts/profile.html index 398d765e..c4df9e77 100755 --- a/_layouts/profile.html +++ b/_layouts/profile.html @@ -1,46 +1,74 @@ --- layout: default --- - + -
-

{% t peoples.name.{{ page.id | split: "/" | last }} %}

+
+
+ {% if page.avatar %} + + {% else %} + + {% endif %} +
+
+
+

{% t people.{{ page.id | split: '/' | last }} %}

+
+ {% if page.site or page.mail or page.scholar or page.orcid or page.scopus or page.elib or page.mathnet %} +
+ {% if page.site %} +
+ + {% t profile.website %} +
+ {% endif %} + + {% if page.mail %} +
+ + {{ page.mail }} +
+ {% endif %} + + {% if page.scholar %} +
+ + Google Scholar +
+ {% endif %} + + {% if page.orcid %} +
+ + ORCID +
+ {% endif %} + + {% if page.scopus %} +
+ + Scopus +
+ {% endif %} + + {% if page.elib %} +
+ + eLibrary +
+ {% endif %} + + {% if page.mathnet %} +
+ + Math-Net +
+ {% endif %} +
+ {% endif %} +
- -{% if page.avatar %} - -{% endif %} - -{% if page.site %} - {% t profile.website %}
-{% endif %} - -{% if page.mail %} - {{ page.mail }}
-{% endif %} - -{% if page.scholar %} - google scholar
-{% endif %} -{% if page.orcid %} - OrcID
-{% endif %} -{% if page.scopus %} - Scopus
-{% endif %} -{% if page.elib %} - eLibrary
-{% endif %} -{% if page.mathnet %} - Math-Net
-{% endif %} -  -
-  - - - - {{ content }} {% assign found = false %} @@ -52,23 +80,20 @@

{% {% endif %} {% endfor %} {% endfor %} - - -{% if found %} -   -
-

{% t profile.teaches %}:

-
- {% for course in site.course %} +{% if found %} +
+

{% t profile.teaches %}

+
+ {% for course in site.course %} {% assign lecturers = course.lecturers | split: "," %} {% for lecturer in lecturers %} {% if page.url contains lecturer %} - - {% endif %} + + {% t courses.{{ course.id | split: '/' | last }} %} + + {% endif %} {% endfor %} {% endfor %} -
-{% endif %} +
+{% endif %} diff --git a/_layouts/redirect.html b/_layouts/redirect.html index accbcf03..df97ff03 100644 --- a/_layouts/redirect.html +++ b/_layouts/redirect.html @@ -1,4 +1,4 @@ - - \ No newline at end of file + + diff --git a/_people/aduenko_aa.md b/_people/aduenko_aa.md index 897f522d..6959c6f4 100644 --- a/_people/aduenko_aa.md +++ b/_people/aduenko_aa.md @@ -1,16 +1,15 @@ --- -title: peoples.title.aduenko_aa -name: peoples.name +title: people.aduenko_aa edit: true position: phd avatar: aduenko_aa.jpg -mail: +mail: site: -scholar: -orcid: -mathnet: -scopus: www.scopus.com/authid/detail.uri?authorId=56922331100 -elib: +scholar: +orcid: +mathnet: +scopus: https://www.scopus.com/authid/detail.uri?authorId=56922331100 +elib: --- {% tf _people/aduenko_aa.md %} diff --git a/_people/apishev_ma.md b/_people/apishev_ma.md index 1a6e3bde..378d82a5 100644 --- a/_people/apishev_ma.md +++ b/_people/apishev_ma.md @@ -1,16 +1,15 @@ --- -title: peoples.title.apishev_ma -name: peoples.name +title: people.apishev_ma edit: true position: phd avatar: apishev_ma.jpg -mail: +mail: site: http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Mapishev -scholar: -orcid: -mathnet: -scopus: www.scopus.com/authid/detail.uri?authorId=57022229800 -elib: +scholar: +orcid: +mathnet: +scopus: https://www.scopus.com/authid/detail.uri?authorId=57022229800 +elib: --- {% tf _people/apishev_ma.md %} diff --git a/_people/bakhteev_oy.md b/_people/bakhteev_oy.md index 58a6fb83..8fda372f 100644 --- a/_people/bakhteev_oy.md +++ b/_people/bakhteev_oy.md @@ -1,16 +1,15 @@ --- -title: peoples.title.bakhteev_oy -name: peoples.name +title: people.bakhteev_oy edit: true position: phd avatar: bakhteev_oy.jpg -mail: bakhteev(at)phystech.edu +mail: bakhteev@phystech.edu site: https://bahleg.github.io -scholar: scholar.google.com/citations?user=7eWNuFkAAAAJ&hl=ru -orcid: +scholar: https://scholar.google.com/citations?user=7eWNuFkAAAAJ&hl=ru +orcid: mathnet: -elib: www.elibrary.ru/author_profile.asp?id=966578 -scopus: www.scopus.com/authid/detail.uri?authorId=57189341556 +elib: https://www.elibrary.ru/author_profile.asp?id=966578 +scopus: https://www.scopus.com/authid/detail.uri?authorId=57189341556 --- {% tf _people/bakhteev_oy.md %} diff --git a/_people/beznosikov_an.md b/_people/beznosikov_an.md deleted file mode 100644 index f957806a..00000000 --- a/_people/beznosikov_an.md +++ /dev/null @@ -1,16 +0,0 @@ ---- -title: peoples.title.beznosikov_an -name: peoples.name -edit: true -position: phd -avatar: noname.jpg -mail: -site: -scholar: -orcid: -mathnet: -elib: -scopus: ---- - -{% tf _people/beznosikov_an.md %} diff --git a/_people/bishuk_ay.md b/_people/bishuk_ay.md index cb71d548..d5a0bc44 100644 --- a/_people/bishuk_ay.md +++ b/_people/bishuk_ay.md @@ -1,16 +1,15 @@ --- -title: peoples.title.bishuk_ay -name: peoples.name +title: people.bishuk_ay edit: true -position: gs +position: pgs avatar: bishuk_ay.jpeg mail: anton.bishuk@mail.ru -site: -scholar: -orcid: -mathnet: -scopus: -elib: +site: +scholar: +orcid: +mathnet: +scopus: +elib: --- {% tf _people/bishuk_ay.md %} diff --git a/_people/chekhovich_yv.md b/_people/chekhovich_yv.md index 0ad764d7..ccb8af6c 100644 --- a/_people/chekhovich_yv.md +++ b/_people/chekhovich_yv.md @@ -1,16 +1,15 @@ --- -title: peoples.title.chekhovich_yv -name: peoples.name +title: people.chekhovich_yv edit: true position: phd avatar: chekhovich_yv.jpg -mail: +mail: site: http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Yury_Chekhovich -scholar: scholar.google.com/citations?hl=ru&user=aYNqZnsAAAAJ +scholar: https://scholar.google.com/citations?hl=ru&user=aYNqZnsAAAAJ orcid: mathnet: -scopus: www.scopus.com/authid/detail.uri?authorId=6507286315 -elib: www.elibrary.ru/author_items.asp?authorid=17499&pubrole=100&show_refs=1&show_option=0 +scopus: https://www.scopus.com/authid/detail.uri?authorId=6507286315 +elib: https://www.elibrary.ru/author_items.asp?authorid=17499&pubrole=100&show_refs=1&show_option=0 --- {% tf _people/chekhovich_yv.md %} diff --git a/_people/dorin_dd.md b/_people/dorin_dd.md new file mode 100644 index 00000000..baaaf3df --- /dev/null +++ b/_people/dorin_dd.md @@ -0,0 +1,15 @@ +--- +title: people.dorin_dd +edit: true +position: gs +avatar: dorin_dd.jpeg +mail: dorin.dd@phystech.edu +site: +scholar: https://scholar.google.com/citations?user=LbVyeRgAAAAJ +orcid: +mathnet: +scopus: +elib: https://www.elibrary.ru/author_items.asp?authorid=1305582 +--- + +{% tf _people/dorin_dd.md %} diff --git a/_people/dulin_sk.md b/_people/dulin_sk.md index 97c0d97a..34988d10 100644 --- a/_people/dulin_sk.md +++ b/_people/dulin_sk.md @@ -1,16 +1,15 @@ --- -title: peoples.title.dulin_sk -name: peoples.name +title: people.dulin_sk edit: true position: dos avatar: dulin_sk.png -mail: +mail: site: http://www.ras.ru/win/DB/show_per.asp?P=.id-3960.ln-ru -scholar: +scholar: orcid: -mathnet: www.mathnet.ru/eng/person17884 -scopus: www.scopus.com/authid/detail.uri?authorId=6701703164 -elib: www.elibrary.ru/author_items.asp?authorid=3320&pubrole=100&show_refs=1&show_option=0 +mathnet: https://www.mathnet.ru/eng/person17884 +scopus: https://www.scopus.com/authid/detail.uri?authorId=6701703164 +elib: https://www.elibrary.ru/author_items.asp?authorid=3320&pubrole=100&show_refs=1&show_option=0 --- {% tf _people/dulin_sk.md %} diff --git a/_people/filatov_av.md b/_people/filatov_av.md index ec33e1e8..14dd0416 100644 --- a/_people/filatov_av.md +++ b/_people/filatov_av.md @@ -1,15 +1,14 @@ --- -title: peoples.title.filatov_av -name: peoples.name +title: people.filatov_av edit: true -position: gs +position: pgs avatar: filatov_av.jpg mail: filatovandreiv@gmail.com -site: -scholar: scholar.google.com/citations?user=xRNTrdcAAAAJ -orcid: -mathnet: -scopus: +site: +scholar: https://scholar.google.com/citations?user=xRNTrdcAAAAJ +orcid: +mathnet: +scopus: elib: --- diff --git a/_people/firsov_sa.md b/_people/firsov_sa.md new file mode 100644 index 00000000..1804876d --- /dev/null +++ b/_people/firsov_sa.md @@ -0,0 +1,15 @@ +--- +title: people.firsov_sa +edit: true +position: gs +avatar: firsov_sa.jpg +mail: firsov.sa@phystech.edu +site: https://t.me/schafts +scholar: +orcid: +mathnet: +scopus: +elib: +--- + +{% tf _people/firsov_sa.md %} diff --git a/_people/gneushev_an.md b/_people/gneushev_an.md index 7b57271b..92216a13 100644 --- a/_people/gneushev_an.md +++ b/_people/gneushev_an.md @@ -1,15 +1,14 @@ --- -title: peoples.title.gneushev_an -name: peoples.name +title: people.gneushev_an edit: true position: phd avatar: gneushev_an.jpg -mail: +mail: site: http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Algneushev -scholar: scholar.google.com/citations?hl=ru&user=sjlY2q8AAAAJ +scholar: https://scholar.google.com/citations?hl=ru&user=sjlY2q8AAAAJ orcid: elib: https://www.elibrary.ru/author_items.asp?authorid=298568 -mathnet: www.mathnet.ru/rus/person72735 +mathnet: https://www.mathnet.ru/rus/person72735 --- {% tf _people/gneushev_an.md %} diff --git a/_people/grabovoy_av.md b/_people/grabovoy_av.md index 8dcf3fce..b2cffa8e 100755 --- a/_people/grabovoy_av.md +++ b/_people/grabovoy_av.md @@ -1,15 +1,14 @@ --- -title: peoples.title.grabovoy_av -name: peoples.name +title: people.grabovoy_av edit: true position: phd avatar: grabovoy_av.jpg mail: grabovoy.av@phystech.edu -site: andriygav.github.io -scholar: scholar.google.com/citations?user=ZtI9pgsAAAAJ&hl=ru -orcid: orcid.org/0000-0002-4031-0025 -mathnet: mathnet.ru/php/person.phtml?option_lang=rus&personid=151213 -scopus: www.scopus.com/authid/detail.uri?authorId=57209653601 +site: https://andriygav.github.io +scholar: https://scholar.google.com/citations?user=ZtI9pgsAAAAJ&hl=ru +orcid: https://orcid.org/0000-0002-4031-0025 +mathnet: https://mathnet.ru/php/person.phtml?option_lang=rus&personid=151213 +scopus: https://www.scopus.com/authid/detail.uri?authorId=57209653601 --- {% tf _people/grabovoy_av.md %} diff --git a/_people/grebenkova_os.md b/_people/grebenkova_os.md index 828511ba..529debd3 100644 --- a/_people/grebenkova_os.md +++ b/_people/grebenkova_os.md @@ -1,16 +1,15 @@ --- -title: peoples.title.grebenkova_os -name: peoples.name +title: people.grebenkova_os edit: true -position: gs +position: pgs avatar: grebenkova_os.jpg mail: grebenkova.os@phystech.edu -site: -scholar: +site: +scholar: orcid: -mathnet: -scopus: -elib: +mathnet: +scopus: +elib: --- {% tf _people/grebenkova_os.md %} diff --git a/_people/grishanov_av.md b/_people/grishanov_av.md index 195d91a3..e5d3a89c 100644 --- a/_people/grishanov_av.md +++ b/_people/grishanov_av.md @@ -1,13 +1,12 @@ --- -title: peoples.title.grishanov_av -name: peoples.name +title: people.grishanov_av edit: true -position: gs +position: pgs avatar: grishanov_av.jpeg mail: grishanov.av@phystech.edu site: -scholar: scholar.google.com/citations?user=LLgj-U4AAAAJ&hl=en -orcid: orcid.org/0000-0001-5085-060X/print +scholar: https://scholar.google.com/citations?user=LLgj-U4AAAAJ&hl=en +orcid: https://orcid.org/0000-0001-5085-060X/print mathnet: scopus: --- diff --git a/_people/isachenko_rv.md b/_people/isachenko_rv.md index c820369f..a3fef29e 100644 --- a/_people/isachenko_rv.md +++ b/_people/isachenko_rv.md @@ -1,15 +1,14 @@ --- -title: peoples.title.isachenko_rv -name: peoples.name +title: people.isachenko_rv edit: true position: phd avatar: isachenko_rv.jpg -mail: roman.isachenko(at)phystech.edu +mail: roman.isachenko@phystech.edu site: -scholar: scholar.google.com/citations?hl=ru&user=Y5W_zrEAAAAJ -orcid: +scholar: +orcid: https://orcid.org/0000-0002-6361-0784 mathnet: -scopus: www.scopus.com/authid/detail.uri?authorId=57193081948 +scopus: https://www.scopus.com/authid/detail.uri?authorId=57193081948 --- {% tf _people/isachenko_rv.md %} diff --git a/_people/kasyuk_va.md b/_people/kasyuk_va.md new file mode 100644 index 00000000..f2145897 --- /dev/null +++ b/_people/kasyuk_va.md @@ -0,0 +1,15 @@ +--- +title: people.kasyuk_va +edit: true +position: gs +avatar: kasyuk_va.jpeg +mail: kasiuk.va@phystech.edu +site: +scholar: +orcid: +mathnet: +scopus: +elib: +--- + +{% tf _people/kasyuk_va.md %} diff --git a/_people/khoroshevsky_vf.md b/_people/khoroshevsky_vf.md index 7870310b..37a2f829 100644 --- a/_people/khoroshevsky_vf.md +++ b/_people/khoroshevsky_vf.md @@ -1,15 +1,14 @@ --- -title: peoples.title.khoroshevsky_vf -name: peoples.name +title: people.khoroshevsky_vf edit: true position: dos avatar: khoroshevsky_vf.jpg -mail: +mail: site: -scholar: scholar.google.com/citations?hl=ru&user=g7kYtbUAAAAJ +scholar: https://scholar.google.com/citations?hl=ru&user=g7kYtbUAAAAJ orcid: -mathnet: -elib: www.elibrary.ru/author_profile.asp?id=131 +mathnet: +elib: https://www.elibrary.ru/author_profile.asp?id=131 --- {% tf _people/khoroshevsky_vf.md %} diff --git a/_people/khrilchenko_ky.md b/_people/khrilchenko_ky.md index 17234e1c..fdab1e08 100644 --- a/_people/khrilchenko_ky.md +++ b/_people/khrilchenko_ky.md @@ -1,8 +1,7 @@ --- -title: peoples.title.khrilchenko_ky -name: peoples.name +title: people.khrilchenko_ky edit: true -position: gs +position: pgs avatar: khrilchenko_ky.jpg mail: site: diff --git a/_people/khritankov_as.md b/_people/khritankov_as.md index 22bf5786..9186bc73 100644 --- a/_people/khritankov_as.md +++ b/_people/khritankov_as.md @@ -1,16 +1,15 @@ --- -title: peoples.title.khritankov_as -name: peoples.name +title: people.khritankov_as edit: true position: phd avatar: khritankov_as.jpg mail: -site: -scholar: scholar.google.com/citations?hl=ru&user=OtxWKpMAAAAJ -orcid: -elib: elibrary.ru/author_profile.asp?id=969204 -scopus: scopus.com/authid/detail.uri?authorId=36237523300 -mathnet: +site: +scholar: https://scholar.google.com/citations?hl=ru&user=OtxWKpMAAAAJ +orcid: +elib: https://elibrary.ru/author_profile.asp?id=969204 +scopus: https://scopus.com/authid/detail.uri?authorId=36237523300 +mathnet: --- {% tf _people/khritankov_as.md %} diff --git a/_people/kiselev_ns.md b/_people/kiselev_ns.md new file mode 100644 index 00000000..27f3d9ce --- /dev/null +++ b/_people/kiselev_ns.md @@ -0,0 +1,15 @@ +--- +title: people.kiselev_ns +edit: true +position: gs +avatar: kiselev_ns.jpg +mail: kiselev.ns@phystech.edu +site: https://kisnikser.github.io/ +scholar: https://scholar.google.com/citations?user=8BOqs70AAAAJ +orcid: +mathnet: +scopus: +elib: https://elibrary.ru/author_items.asp?authorid=1303715 +--- + +{% tf _people/kiselev_ns.md %} diff --git a/_people/kreinin_mv.md b/_people/kreinin_mv.md new file mode 100644 index 00000000..68f21064 --- /dev/null +++ b/_people/kreinin_mv.md @@ -0,0 +1,15 @@ +--- +title: people.kreinin_mv +edit: true +position: gs +avatar: kreinin_mv.jpeg +mail: kreinin.mv@phystech.edu +site: https://www.linkedin.com/in/kreininmv/ +scholar: +orcid: +mathnet: +scopus: +elib: +--- + +{% tf _people/kreinin_mv.md %} diff --git a/_people/kropotov_da.md b/_people/kropotov_da.md index bcb15944..83172c86 100644 --- a/_people/kropotov_da.md +++ b/_people/kropotov_da.md @@ -1,16 +1,15 @@ --- -title: peoples.title.kropotov_da -name: peoples.name +title: people.kropotov_da edit: true position: phd avatar: kropotov_da.jpg mail: site: -scholar: scholar.google.com/citations?hl=ru&user=R9Xgs2IAAAAJ +scholar: https://scholar.google.com/citations?hl=ru&user=R9Xgs2IAAAAJ orcid: mathnet: -elib: elibrary.ru/author_profile.asp?id=126077 -scopus: scopus.com/authid/detail.uri?authorId=56414713100 +elib: https://elibrary.ru/author_profile.asp?id=126077 +scopus: https://scopus.com/authid/detail.uri?authorId=56414713100 --- {% tf _people/kropotov_da.md %} diff --git a/_people/matveev_ia.md b/_people/matveev_ia.md index 242a0d33..5d83dbae 100644 --- a/_people/matveev_ia.md +++ b/_people/matveev_ia.md @@ -1,16 +1,15 @@ --- -title: peoples.title.matveev_ia -name: peoples.name +title: people.matveev_ia edit: true position: dos -avatar: matveev_ia.jpg -mail: +avatar: matveev_ia.jpg +mail: site: -scholar: scholar.google.com/citations?hl=ru&user=vkU__7EAAAAJ -orcid: -mathnet: -scopus: www.scopus.com/authid/detail.uri?authorId=7007130523 -elib: www.elibrary.ru/author_items.asp?authorid=12119&pubrole=100&show_refs=1&show_option=0 +scholar: https://scholar.google.com/citations?hl=ru&user=vkU__7EAAAAJ +orcid: +mathnet: +scopus: https://www.scopus.com/authid/detail.uri?authorId=7007130523 +elib: https://www.elibrary.ru/author_items.asp?authorid=12119&pubrole=100&show_refs=1&show_option=0 --- {% tf _people/matveev_ia.md %} diff --git a/_people/mestetskiy_lm.md b/_people/mestetskiy_lm.md index a33a6145..1eadf9d8 100644 --- a/_people/mestetskiy_lm.md +++ b/_people/mestetskiy_lm.md @@ -1,6 +1,5 @@ --- -title: peoples.title.mestetskiy_lm -name: peoples.name +title: people.mestetskiy_lm edit: true position: dos avatar: mestetskiy_lm.jpg @@ -9,8 +8,8 @@ site: http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%8 scholar: orcid: mathnet: -scopus: www.scopus.com/authid/detail.uri?authorId=25825277100 -elib: www.elibrary.ru/author_profile.asp?id=8008 +scopus: https://www.scopus.com/authid/detail.uri?authorId=25825277100 +elib: https://www.elibrary.ru/author_profile.asp?id=8008 --- {% tf _people/mestetskiy_lm.md %} diff --git a/_people/meysuradze_ai.md b/_people/meysuradze_ai.md index 44fd0592..3f32c845 100644 --- a/_people/meysuradze_ai.md +++ b/_people/meysuradze_ai.md @@ -1,6 +1,5 @@ --- -title: peoples.title.meysuradze_ai -name: peoples.name +title: people.meysuradze_ai edit: true position: phd avatar: meysuradze_ai.jpg @@ -9,8 +8,8 @@ site: scholar: orcid: mathnet: -scopus: www.scopus.com/authid/detail.uri?authorId=14041971900 -elib: www.elibrary.ru/author_items.asp?authorid=12794&pubrole=100&show_refs=1&show_option=0 +scopus: https://www.scopus.com/authid/detail.uri?authorId=14041971900 +elib: https://www.elibrary.ru/author_items.asp?authorid=12794&pubrole=100&show_refs=1&show_option=0 --- {% tf _people/meysuradze_ai.md %} diff --git a/_people/mohonko_ez.md b/_people/mohonko_ez.md index 5f814b06..426f97bc 100644 --- a/_people/mohonko_ez.md +++ b/_people/mohonko_ez.md @@ -1,16 +1,14 @@ --- -title: peoples.title.mohonko_ez -name: peoples.name +title: people.mohonko_ez edit: true position: dos avatar: mohonko_ez.jpg -mail: +mail: site: -scholar: +scholar: orcid: -mathnet: -elib: www.elibrary.ru/author_items.asp?authorid=4762&pubrole=100&show_refs=1&show_option=0 - +mathnet: +elib: https://www.elibrary.ru/author_items.asp?authorid=4762&pubrole=100&show_refs=1&show_option=0 --- {% tf _people/mohonko_ez.md %} diff --git a/_people/mokrov_pv.md b/_people/mokrov_pv.md index 989a35cf..9546fdf1 100644 --- a/_people/mokrov_pv.md +++ b/_people/mokrov_pv.md @@ -1,16 +1,15 @@ --- -title: peoples.title.mokrov_pv -name: peoples.name +title: people.mokrov_pv edit: true -position: gs +position: pgs avatar: mokrov_pv.jpg mail: mokrov.pv@phystech.edu site: https://github.com/PetrMokrov scholar: https://scholar.google.com/citations?user=CRsi4IkAAAAJ&hl=en -orcid: +orcid: mathnet: -elib: -scopus: +elib: +scopus: --- {% tf _people/mokrov_pv.md %} diff --git a/_people/morozov_ma.md b/_people/morozov_ma.md new file mode 100644 index 00000000..f02b13a9 --- /dev/null +++ b/_people/morozov_ma.md @@ -0,0 +1,15 @@ +--- +title: people.morozov_ma +edit: true +position: pgs +avatar: morozov_ma.jpg +mail: +site: https://www.linkedin.com/in/matveymor/ +scholar: +orcid: +mathnet: +scopus: +elib: +--- + +{% tf _people/morozov_ma.md %} diff --git a/_people/nikitina_ma.md b/_people/nikitina_ma.md new file mode 100644 index 00000000..23c44f88 --- /dev/null +++ b/_people/nikitina_ma.md @@ -0,0 +1,15 @@ +--- +title: people.nikitina_ma +edit: true +position: gs +avatar: nikitina_ma.jpeg +mail: nikitina.maria@phystech.edu +site: +scholar: +orcid: +mathnet: +scopus: +elib: +--- + +{% tf _people/nikitina_ma.md %} diff --git a/_people/panchenko_sk.md b/_people/panchenko_sk.md new file mode 100644 index 00000000..388dc7fe --- /dev/null +++ b/_people/panchenko_sk.md @@ -0,0 +1,15 @@ +--- +title: people.panchenko_sk +edit: true +position: pgs +avatar: panchenko_sk.jpg +mail: +site: +scholar: +orcid: +mathnet: +scopus: +elib: +--- + +{% tf _people/panchenko_sk.md %} diff --git a/_people/popov_as.md b/_people/popov_as.md index 69319f41..61b4c3f3 100644 --- a/_people/popov_as.md +++ b/_people/popov_as.md @@ -1,12 +1,11 @@ --- -title: peoples.title.popov_as -name: peoples.name +title: people.popov_as edit: true -position: gs +position: pgs avatar: popov_as.png mail: site: http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Arti_lehtonen -scholar: scholar.google.com/citations?hl=ru&user=B-QCwLUAAAAJ +scholar: https://scholar.google.com/citations?hl=ru&user=B-QCwLUAAAAJ orcid: mathnet: --- diff --git a/_people/potanin_ms.md b/_people/potanin_ms.md index 30250901..bb4d8727 100644 --- a/_people/potanin_ms.md +++ b/_people/potanin_ms.md @@ -1,12 +1,11 @@ --- -title: peoples.title.potanin_ms -name: peoples.name +title: people.potanin_ms edit: true -position: gs +position: pgs avatar: potanin_ms.jpg mail: site: -scholar: scholar.google.com/citations?hl=ru&user=F9T_I50AAAAJ +scholar: https://scholar.google.com/citations?hl=ru&user=F9T_I50AAAAJ orcid: mathnet: --- diff --git a/_people/samokhina_am.md b/_people/samokhina_am.md index 768fa66d..9a5b9c19 100644 --- a/_people/samokhina_am.md +++ b/_people/samokhina_am.md @@ -1,8 +1,7 @@ --- -title: peoples.title.samokhina_am -name: peoples.name +title: people.samokhina_am edit: true -position: gs +position: pgs avatar: samokhina_am.jpg mail: alina.samokhina@phystech.edu site: https://github.com/Alina-Samokhina diff --git a/_people/severilov_pa.md b/_people/severilov_pa.md index dd513e85..0218859b 100644 --- a/_people/severilov_pa.md +++ b/_people/severilov_pa.md @@ -1,12 +1,11 @@ --- -title: peoples.title.severilov_pa -name: peoples.name +title: people.severilov_pa edit: true -position: gs +position: pgs avatar: severilov_pa.jpg mail: severilov.pa@phystech.edu site: -scholar: +scholar: orcid: mathnet: scopus: diff --git a/_people/strijov_vv.md b/_people/strijov_vv.md index 7cb7f4ba..3abbcf51 100644 --- a/_people/strijov_vv.md +++ b/_people/strijov_vv.md @@ -1,16 +1,15 @@ --- -title: peoples.title.strijov_vv -name: peoples.name +title: people.strijov_vv edit: true position: dos avatar: strijov_vv.jpg mail: strijov@ccas.ru site: http://ccas.ru/strijov/ -scholar: scholar.google.com/citations?user=3TpENmIAAAAJ&hl=en&oi=ao -orcid: orcid.org/0000-0002-2194-8859/print -mathnet: www.mathnet.ru/php/person.phtml?option_lang=rus&personid=71984 -scopus: www.scopus.com/authid/detail.uri?authorId=35796373700 -elib: www.elibrary.ru/author_profile.asp?id=16834 +scholar: https://scholar.google.com/citations?user=3TpENmIAAAAJ&hl=en&oi=ao +orcid: https://orcid.org/0000-0002-2194-8859/print +mathnet: https://www.mathnet.ru/php/person.phtml?option_lang=rus&personid=71984 +scopus: https://www.scopus.com/authid/detail.uri?authorId=35796373700 +elib: https://www.elibrary.ru/author_profile.asp?id=16834 --- {% tf _people/strijov_vv.md %} diff --git a/_people/tikhonov_dm.md b/_people/tikhonov_dm.md index 1be6b6e7..40cac08a 100644 --- a/_people/tikhonov_dm.md +++ b/_people/tikhonov_dm.md @@ -1,12 +1,11 @@ --- -title: peoples.title.tikhonov_dm -name: peoples.name +title: people.tikhonov_dm edit: true -position: gs -avatar: +position: pgs +avatar: tikhonov_dm.jpeg mail: tihonov.dm@phystech.edu site: -scholar: +scholar: orcid: mathnet: scopus: diff --git a/_people/torshin_iy.md b/_people/torshin_iy.md index ca28075e..5b2ec41f 100644 --- a/_people/torshin_iy.md +++ b/_people/torshin_iy.md @@ -1,16 +1,15 @@ --- -title: peoples.title.torshin_iy -name: peoples.name +title: people.torshin_iy edit: true position: phd avatar: torshin_iy.png -mail: +mail: site: http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Tiy -scholar: -orcid: -mathnet: -elib: www.elibrary.ru/author_items.asp?authorid=54104&pubrole=100&show_refs=1&show_option=0 -scopus: www.scopus.com/authid/detail.uri?authorId=7003300274 +scholar: +orcid: +mathnet: +elib: https://www.elibrary.ru/author_items.asp?authorid=54104&pubrole=100&show_refs=1&show_option=0 +scopus: https://www.scopus.com/authid/detail.uri?authorId=7003300274 --- {% tf _people/torshin_iy.md %} diff --git a/_people/tsurkov_vi.md b/_people/tsurkov_vi.md index 4657f36f..2426b608 100644 --- a/_people/tsurkov_vi.md +++ b/_people/tsurkov_vi.md @@ -1,16 +1,15 @@ --- -title: peoples.title.tsurkov_vi -name: peoples.name +title: people.tsurkov_vi edit: true position: dos avatar: tsurkov_vi.jpeg -mail: +mail: site: https://ru.wikipedia.org/wiki/%D0%A6%D1%83%D1%80%D0%BA%D0%BE%D0%B2,_%D0%92%D0%BB%D0%B0%D0%B4%D0%B8%D0%BC%D0%B8%D1%80_%D0%98%D0%B2%D0%B0%D0%BD%D0%BE%D0%B2%D0%B8%D1%87 -scholar: scholar.google.com/citations?hl=ru&user=rmFfBWAAAAAJ +scholar: https://scholar.google.com/citations?hl=ru&user=rmFfBWAAAAAJ orcid: -mathnet: -elib: www.elibrary.ru/author_profile.asp?id=147 -scopus: www.scopus.com/authid/detail.uri?authorId=7004468001 +mathnet: +elib: https://www.elibrary.ru/author_profile.asp?id=147 +scopus: https://www.scopus.com/authid/detail.uri?authorId=7004468001 --- {% tf _people/tsurkov_vi.md %} diff --git a/_people/vladimirov_ea.md b/_people/vladimirov_ea.md new file mode 100644 index 00000000..ab0529d5 --- /dev/null +++ b/_people/vladimirov_ea.md @@ -0,0 +1,15 @@ +--- +title: people.vladimirov_ea +edit: true +position: pgs +avatar: vladimirov_ea.jpeg +mail: +site: +scholar: +orcid: +mathnet: +scopus: +elib: +--- + +{% tf _people/vladimirov_ea.md %} diff --git a/_people/volodkevich_aa.md b/_people/volodkevich_aa.md index 20d5f8ef..9b1d0c41 100644 --- a/_people/volodkevich_aa.md +++ b/_people/volodkevich_aa.md @@ -1,16 +1,15 @@ --- -title: peoples.title.volodkevich_aa -name: peoples.name +title: people.volodkevich_aa edit: true -position: gs +position: pgs avatar: volodkevich_aa.jpg mail: -site: -scholar: +site: +scholar: orcid: -mathnet: -scopus: -elib: +mathnet: +scopus: +elib: --- {% tf _people/volodkevich_aa.md %} diff --git a/_people/vorontsov_kv.md b/_people/vorontsov_kv.md index 829ebc20..f28e4f64 100644 --- a/_people/vorontsov_kv.md +++ b/_people/vorontsov_kv.md @@ -1,17 +1,15 @@ --- -id: vorontsov_kv -title: peoples.title.vorontsov_kv -name: peoples.name +title: people.vorontsov_kv edit: true -position: dos,hotd +position: hotd avatar: vorontsov_kv.jpg mail: -site: www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Vokov -scholar: scholar.google.com/citations?user=KIW4fnsAAAAJ&hl=ru&oi=ao +site: http://www.machinelearning.ru/wiki/index.php?title=%D0%A3%D1%87%D0%B0%D1%81%D1%82%D0%BD%D0%B8%D0%BA:Vokov +scholar: https://scholar.google.com/citations?user=KIW4fnsAAAAJ&hl=ru&oi=ao orcid: mathnet: -elib: www.elibrary.ru/author_items.asp?authorid=15081&pubrole=100&show_refs=1&show_option=0 -scopus: www.scopus.com/authid/detail.uri?authorId=6507982932 +elib: https://www.elibrary.ru/author_items.asp?authorid=15081&pubrole=100&show_refs=1&show_option=0 +scopus: https://www.scopus.com/authid/detail.uri?authorId=6507982932 --- {% tf _people/vorontsov_kv.md %} diff --git a/_people/yakovlev_kd.md b/_people/yakovlev_kd.md index 0d20aeae..cd983546 100644 --- a/_people/yakovlev_kd.md +++ b/_people/yakovlev_kd.md @@ -1,13 +1,12 @@ --- -title: peoples.title.yakovlev_kd -name: peoples.name +title: people.yakovlev_kd edit: true -position: gs -avatar: noname.jpg -mail: -site: -scholar: -orcid: +position: pgs +avatar: yakovlev_kd.jpg +mail: yakovlev.kd@phystech.edu +site: https://www.hse.ru/en/org/persons/950725636/ +scholar: https://scholar.google.com/citations?user=S3P0l0MAAAAJ&hl=en +orcid: https://orcid.org/0009-0005-9397-6081 mathnet: scopus: elib: diff --git a/_sass/_admission.scss b/_sass/_admission.scss new file mode 100644 index 00000000..5280d16f --- /dev/null +++ b/_sass/_admission.scss @@ -0,0 +1,27 @@ +.task-block { + display: block; + font-size: $font-size-base; + font-family: $font-primary; + border-radius: 1rem; + padding: 0.5rem 1rem; + margin: 1rem 0; + border-left: 10px solid #f5f5f5; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; + + &:hover, + &:focus { + background-color: #f5f5f5; + } +} + +.task-block-title { + font-weight: 600; + margin-bottom: 0; +} diff --git a/_sass/_course.scss b/_sass/_course.scss index 9c1df0d3..243e88f8 100644 --- a/_sass/_course.scss +++ b/_sass/_course.scss @@ -5,26 +5,27 @@ margin-bottom: 2em; } -.list-course { - padding: 10px; -} - .list-item-course { display: block; - padding: 7px 20px; - margin-bottom: 10px; - margin-top: 10px; - border-radius: 6px; - border-left: 10px solid #cfdee3; - box-shadow: 2px -2px 5px 0 rgba(0,0,0,0.05), - -2px -2px 5px 0 rgba(0,0,0,0.05), - 2px 2px 5px 0 rgba(0,0,0,0.05), - -2px 2px 5px 0 rgba(0,0,0,0.05); -} + font-family: $font-primary; + border-radius: 1rem; + padding: 0.75rem; + margin: 0.25rem 0; + border-left: 10px solid #f5f5f5; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; -.list-item-course:hover { - background-color: #cfdfe3; - cursor: pointer; + &:hover, + &:focus { + background-color: #f5f5f5; + cursor: pointer; + } } .list-item-course-title img { @@ -32,21 +33,60 @@ margin-top: 1.25em; } -.list-item-course-title { - font-size: 18px; -} - .list-item-course-title { - color: black; + font-size: $font-size-name; margin: 0px; } a.course-name { - color: inherit; - font-size: 18px; - + text-decoration: none; + &:hover, + &:focus { + color: $href-color; + } +} + +// Кнопка для ссылки на сайт курса +.course-website-link { + // font-family: $font-primary; + font-size: $font-size-name; + display: inline-block; + border-radius: 1rem; + padding: 0.5rem 0.75rem; + margin: 0.25rem 0; + border-left: 10px solid #f5f5f5; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + text-decoration: none; + + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; + &:hover, &:focus { + background-color: #f5f5f5; + cursor: pointer; + } + + i { + margin-right: 8px; + color: $href-color; + } + + &:hover, + &:focus { + background-color: #f5f5f5; text-decoration: none; } -} \ No newline at end of file +} + +// Минималистичный разделитель секций +.course-section-divider { + margin-top: 3em; + margin-bottom: 2em; + height: 1px; + background: linear-gradient(to right, transparent, #e0e0e0 20%, #e0e0e0 80%, transparent); +} diff --git a/_sass/_fade_in.scss b/_sass/_fade_in.scss new file mode 100644 index 00000000..1725ebf6 --- /dev/null +++ b/_sass/_fade_in.scss @@ -0,0 +1,115 @@ +// Fade-in animations for scroll effects + +// Page fade-in on load +body { + opacity: 0; + transition: opacity 0.3s ease-in; +} + +body.page-loaded { + opacity: 1; +} + +// Respect user's motion preferences +@media (prefers-reduced-motion: reduce) { + body { + opacity: 1; + transition: none; + } +} + +// Base hidden state +.fade-in-section { + opacity: 0; + transform: translateY(50px); + transition: all 1s ease-out; +} + +// Visible state +.fade-in-section.visible { + opacity: 1; + transform: translateY(0); +} + +// Variants with different directions +.fade-in-left { + opacity: 0; + transform: translateX(-50px); + transition: all 1s ease-out; +} + +.fade-in-left.visible { + opacity: 1; + transform: translateX(0); +} + +.fade-in-right { + opacity: 0; + transform: translateX(50px); + transition: all 1s ease-out; +} + +.fade-in-right.visible { + opacity: 1; + transform: translateX(0); +} + +.fade-in-up { + opacity: 0; + transform: translateY(50px); + transition: all 1s ease-out; +} + +.fade-in-up.visible { + opacity: 1; + transform: translateY(0); +} + +.fade-in-down { + opacity: 0; + transform: translateY(-50px); + transition: all 1s ease-out; +} + +.fade-in-down.visible { + opacity: 1; + transform: translateY(0); +} + +// Scale variant +.fade-in-scale { + opacity: 0; + transform: scale(0.9); + transition: all 1s ease-out; +} + +.fade-in-scale.visible { + opacity: 1; + transform: scale(1); +} + +// Delayed variants for staggered animations +.fade-in-delay-1 { + transition-delay: 0.1s; +} + +.fade-in-delay-2 { + transition-delay: 0.2s; +} + +.fade-in-delay-3 { + transition-delay: 0.3s; +} + +.fade-in-delay-4 { + transition-delay: 0.4s; +} + +// Slower/faster variants +.fade-in-slow { + transition-duration: 1s; +} + +.fade-in-fast { + transition-duration: 0.3s; +} diff --git a/_sass/_footer.scss b/_sass/_footer.scss index 9d250b71..50435c7e 100644 --- a/_sass/_footer.scss +++ b/_sass/_footer.scss @@ -1,7 +1,21 @@ footer { + font-family: $font-primary; + font-size: $font-size-small; width: 100%; color: #777; - font-size: 12px; text-align: center; - padding-bottom: 10px; -} \ No newline at end of file + margin: 10px 0; +} + +a.social { + text-decoration: none; + color: inherit; + font-size: $font-size-footer-icon; + margin: 2px; + + &:hover, + &:focus { + text-decoration: none; + color: $href-color; + } +} diff --git a/_sass/_home.scss b/_sass/_home.scss new file mode 100644 index 00000000..ef13de79 --- /dev/null +++ b/_sass/_home.scss @@ -0,0 +1,315 @@ +.layout-home { + margin: 0 auto; +} + +.news-block { + font-family: $font-primary; + text-align: left; + line-height: 1.4; + display: block; + min-width: 200px; + max-width: 300px; + background: #fff; + border-radius: 1rem; + padding: 1rem; + border-left: 10px solid #f5f5f5; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + text-decoration: none; + color: inherit; + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; + flex-shrink: 0; + position: relative; + + &:hover, + &:focus { + background-color: #f5f5f5; + cursor: pointer; + text-decoration: none; + color: inherit; + + .news-title { + color: $href-color; + } + } +} + +.news-title { + font-size: 1rem; + font-weight: 600; + text-align: left; + margin-bottom: 0.2rem; + transition: color 0.2s ease; + color: inherit; +} + +.news-date { + font-family: $font-primary; + color: #777; + font-size: 1rem; + margin-bottom: 0.5rem; +} + +.news-excerpt { + color: #555; + font-size: 1rem; + margin-bottom: 0px; +} + +.news-important-badge { + position: absolute; + top: 0rem; + right: -1rem; + background: $href-bg-color; + color: $href-color; + font-weight: 600; + padding: 0.4rem 1.2rem; + border-radius: 0.5rem; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + transform: rotate(15deg); + pointer-events: none; +} + +.research-block { + display: block; + font-family: $font-primary; + border-radius: 1rem; + padding: 2rem; + border-left: 10px solid #f5f5f5; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; + + &:hover, + &:focus { + background-color: #f5f5f5; + } + + a { + text-decoration: none; + color: inherit; + + &:hover, + &:focus { + text-decoration: none; + color: $href-color; + } + } +} + +.research-block-title { + font-size: $font-size-h3; + font-weight: 600; + text-align: left; + transition: color 0.2s ease; +} + +.carousel-item { + font-family: $font-primary; + padding: 2rem; + display: flex; + flex-direction: column; + align-items: center; + justify-content: center; + min-height: 600px; /* Фиксированная высота контейнера */ + width: 100%; /* Ограничиваем ширину */ + max-width: 100%; /* Не даем выйти за границы */ + overflow: hidden; /* Скрываем все, что выходит за границы */ +} + +.carousel-item img { + max-height: 500px; + max-width: 100%; + width: auto; + height: auto; + object-fit: contain; /* Сохраняем пропорции */ + border-radius: 5px; +} + +#carousel-section { + width: 100%; + max-width: 100%; + overflow-x: hidden; /* Только горизонтальный overflow */ +} + +#carousel-section .carousel, +#carousel-section .slider-container { + margin: 0 auto; /* Центрируем карусель */ +} + +#carousel-section .container { + flex-grow: 1; + margin: 0 auto; /* Центрируем контейнер */ + position: relative; + width: 100%; + max-width: 100%; + padding: 0 1rem; /* Добавляем отступы по бокам */ +} + +/* Убираем адаптивные ограничения ширины для карусели */ +/* Карусель всегда занимает всю доступную ширину и центрируется */ +@media screen and (min-width: 1024px) { + #carousel-section .container { + max-width: 100%; + padding: 0 2rem; + } +} + +@media screen and (min-width: 1216px) { + #carousel-section .container { + max-width: 100%; + padding: 0 3rem; + } +} + +@media screen and (min-width: 1408px) { + #carousel-section .container { + max-width: 100%; + padding: 0 4rem; + } +} + +/* Стили для стрелок навигации карусели */ +/* Центрируем стрелки по изображению, а не по всему блоку */ +#carousel-section .slider-navigation-previous, +#carousel-section .slider-navigation-next { + /* Рассчитываем позицию: половина высоты контейнера минус половина высоты подписи */ + top: calc(50% - 1.5rem) !important; /* вычитаем примерно половину высоты подписи */ + transform: translateY(-50%); +} + +/* Адаптивные размеры для мобильных */ +@media screen and (max-width: 768px) { + .carousel-item { + min-height: 400px; + padding: 1rem; + } + + .carousel-item img { + max-height: 300px; + } + + /* Стрелки навигации на мобильных - по центру изображения */ + #carousel-section .slider-navigation-previous, + #carousel-section .slider-navigation-next { + top: calc(50% - 1.5rem) !important; + transform: translateY(-50%); + } +} + +/* Conference Card Styles */ +.conference-card { + font-family: $font-primary; + font-size: $font-size-base; + background: #fff; + border-radius: 1rem; + padding: 1rem; + border-left: 10px solid #f5f5f5; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; + text-decoration: none; + color: inherit; + display: block; + cursor: pointer; + + &:hover, + &:focus { + background-color: #f5f5f5; + text-decoration: none; + color: inherit; + + h4 { + color: $href-color; + } + } + + h4 { + color: inherit; + font-size: $font-size-h4; + font-weight: 600; + margin: 0 0 0.8rem 0; + transition: color 0.2s ease; + } + + .conference-name { + display: flex; + justify-content: space-between; + align-items: start; + margin-bottom: 0.8rem; + } + + .conference-rank { + background: #f0f0f0; + padding: 0.25rem 0.75rem; + border-radius: 20px; + font-weight: 600; + color: #666; + } + + .conference-full-name { + opacity: 0.85; + margin-bottom: 1rem; + color: inherit; + } + + .conference-deadline-box { + background: #f5f5f5; + border-radius: 8px; + padding: 1rem; + margin-bottom: 1rem; + border-left: 3px solid #ddd; + + .deadline-label { + opacity: 0.7; + margin-bottom: 0.3rem; + } + + .deadline-date { + font-weight: 600; + } + + .deadline-warning { + margin-top: 0.5rem; + padding: 0.5rem; + background: #fff3cd; + border-radius: 6px; + text-align: center; + font-weight: 600; + color: #856404; + border-left: 3px solid #ffc107; + } + } + + .conference-info { + opacity: 0.7; + margin-bottom: 0.5rem; + color: inherit; + } +} + +/* Responsive adjustments for conference cards */ +@media screen and (max-width: $lt-width) { + .conference-card { + font-size: 0.9rem; + padding: 1.5rem; + .conference-deadline-box { + padding: 0.8rem; + } + } +} diff --git a/_sass/_main.scss b/_sass/_main.scss index 64298534..de90eb40 100644 --- a/_sass/_main.scss +++ b/_sass/_main.scss @@ -1,7 +1,8 @@ * { -webkit-box-sizing: border-box; - -moz-box-sizing: border-box; - box-sizing: border-box; + -moz-box-sizing: border-box; + box-sizing: border-box; + font-family: $font-primary; } html, @@ -11,155 +12,165 @@ body { } html { - font-family: "Open Sans", "Source Sans Pro", "Helvetica Neue", Helvetica, Arial, sans-serif; - font-size: 18px; - font-weight: 300; - line-height: 1.6; + font-family: $font-primary; + font-size: $font-size-base; + font-weight: $font-weight-base; + overflow-x: hidden; +} - @media (min-width: 38em) { - font-size: 20px; +@media (max-width: $lt-width) { + html { + font-size: 0.9rem; } } body { - color: #515151; + // color: black; + color: #333; + line-height: 1.6; background-color: #fff; -webkit-text-size-adjust: 100%; - -ms-text-size-adjust: 100%; + -ms-text-size-adjust: 100%; + overflow-x: hidden; + width: 100%; } -.MathJax_Display{ - font-size: 80%; +.MathJax_Display { + font-size: $font-size-math; } a { - color: #268bd2; - text-decoration: none; - + color: inherit; + text-decoration: underline; + transition: color 0.2s ease; &:hover, &:focus { - text-decoration: underline; + color: $href-color; } } -h1, h2, h3, h4, h5, h6 { - margin: auto; - margin-bottom: 1em; - font-weight: 600; - font-family: "Open Sans", "Source Sans Pro"; +h1, +h2, +h3, +h4, +h5, +h6 { + margin: auto 0 1rem 0; + font-family: $font-primary; line-height: 1.1; - color: #333; - letter-spacing: -.025rem; + color: #111; scroll-margin-top: 50px; } h1 { - font-size: 2rem; + font-size: $font-size-h1; } h2 { - font-size: 1.6rem; + font-size: $font-size-h2; } h3 { - font-size: 1.3rem; + font-size: $font-size-h3; } -h4, h5, h6 { - font-size: 1rem; +h4, +h5, +h6 { + font-size: $font-size-h4; } p { - font-family: "Open Sans", "Helvetica Neue", Helvetica; - font-weight: 300; + font-family: $font-primary; margin: 0 0 1rem; - font-size: 0.8rem; + font-size: $font-size-body; } -ul, ol, dl { - font-family: "Open Sans", "Helvetica Neue", Helvetica; - font-weight: 300; - font-size: 0.8rem; - margin-top: 0; - margin-bottom: 1rem; +ul, +ol, +dl { + font-family: $font-primary; + font-size: $font-size-body; } -li > ul > li { - margin-left: 1rem; +/* нормальная типографика списков */ +ul { + list-style-type: disc; /* или circle, если нужно */ + list-style-position: outside; /* ключевая строка */ + padding-left: 1.25rem; /* базовый отступ под маркер */ + margin-left: 0; } -dt { - font-weight: bold; +ol { + list-style-position: outside; + padding-left: 1.5rem; /* цифрам обычно чуть больше */ + margin-left: 0; } -dd { - margin-bottom: .5rem; +li { + text-indent: 0; /* на всякий случай */ + margin-bottom: 0.4rem; /* межстрочный интервал между пунктами */ } -ul { - /*font-family: Helvetica, 'Ubuntu Mono';*/ - font-size: 0.8rem; - list-style: inside circle; - padding-left: 0; - - li { - margin-bottom: .25rem; - } - - ul, - ol { - margin-top: .25rem; - margin-bottom: .5rem; - } +p:has(+ ol), +p:has(+ ul) { + margin-bottom: 0.4rem; } -ul.share-buttons{ - list-style: none; - padding: 0; +/* вложенные списки — чуть глубже */ +li > ul, +li > ol { + margin-top: 0.25rem; + margin-bottom: 0.5rem; + padding-left: 1.25rem; } -ol { - list-style: inside decimal; - padding-left: 0; - - li { - margin-bottom: .25rem; - } - - ul, - ol { - margin-top: .25rem; - margin-bottom: .5rem; - } +/* длинные DOI/URL не ломают разметку */ +li a { + overflow-wrap: anywhere; } p + h1, p + h2, p + h3, +p + h4, +p + h5, +p + h6, ul + h1, ul + h2, ul + h3, +ul + h4, +ul + h5, +ul + h6, ol + h1, ol + h2, -ol + h3 { +ol + h3, +ol + h4, +ol + h5, +ol + h6 { margin-top: 1.5rem; } +ul + p, +ol + p { + margin-top: 1rem; +} + hr { border: 0; - border-top: .5px solid #eee; - border-bottom: .5px solid #eee; - margin: 0px; - padding: 0px; + height: 1px; + background: linear-gradient(to right, transparent, #e0e0e0 20%, #e0e0e0 80%, transparent); + margin: 3em 0 2em 0; + padding: 0; } strong { - color: #333; + color: #111; font-weight: 600; } abbr { - font-size: 80%; + font-size: $font-size-code; font-weight: bold; color: #555; text-transform: uppercase; @@ -173,8 +184,7 @@ abbr[title] { blockquote { padding: 0 0 0 1.5rem; margin: 0 2rem 1rem 0; - //color: #999; - border-left: .5rem; //solid #e5e5e5 + border-left: 0.5rem; p:last-child { margin-bottom: 0; @@ -183,12 +193,12 @@ blockquote { code, pre { - font-family: Monaco, "Courier New", monospace; + font-family: $font-monospace; } code { - padding: .25em .5em; - font-size: 80%; + padding: 0.25em 0.5em; + font-size: $font-size-code; color: #bf616a; background-color: #f9f9f9; border-radius: 3px; @@ -199,7 +209,7 @@ pre { margin-top: 0; margin-bottom: 1rem; padding: 0.5rem; - font-size: .8rem; + font-size: $font-size-body; line-height: 1.4; white-space: pre; white-space: pre-wrap; @@ -210,7 +220,7 @@ pre { pre code { padding: 0; - font-size: 80%; + font-size: $font-size-code; color: inherit; background-color: transparent; } @@ -227,38 +237,130 @@ pre code { img { display: block; - max-width: 200px; margin: 0 0 1rem; border-radius: 5px; } table { - margin-bottom: 1rem; + font-family: $font-primary; + line-height: 1.4; + border-collapse: collapse; width: 100%; - font-size: 70%; + margin: 1.5em 0; + border-radius: 0.25rem; + overflow: hidden; + font-size: $font-size-small; + font-weight: 400; border: 1px solid #e5e5e5; - border-collapse: collapse; + box-shadow: 0 1px 3px rgba(0, 0, 0, 0.05); } -td, -th { - padding: .25rem .5rem; +.table-scroll { + position: relative; + margin: 1.5em 0; + overflow-x: auto; + -webkit-overflow-scrolling: touch; + border-radius: 0.25rem; border: 1px solid #e5e5e5; - font-size: 140%; + box-shadow: 0 1px 3px rgba(0, 0, 0, 0.05); + background-color: #fff; } -tbody tr:nth-child(odd) td, -tbody tr:nth-child(odd) th { - background-color: #f9f9f9; +.table-scroll::after { + content: ""; + position: sticky; + right: 0; + top: 0; + bottom: 0; + width: 1.5rem; + pointer-events: none; + background: linear-gradient(to right, rgba(255, 255, 255, 0), rgba(255, 255, 255, 0.85)); + opacity: 0; + transition: opacity 0.3s ease; +} + +.table-scroll:hover::after, +.table-scroll:focus-within::after { + opacity: 1; +} + +.table-scroll > table { + margin: 0; + width: max-content; + min-width: 100%; + border: none; + box-shadow: none; +} + +table a { + text-decoration: none; + &:hover, + &:focus { + text-decoration: none; + } +} + +th { + background: #f5f5f5; + font-weight: 500; + text-align: left; + padding: 0.75em 1em; + border-bottom: 1px solid #e5e5e5; +} + +td { + padding: 0.75em 1em; + border-bottom: 1px solid #f0f0f0; +} + +th, +td { + max-width: 12rem; + overflow-wrap: anywhere; + word-break: break-word; + white-space: normal; + vertical-align: top; +} + +tr:last-child td { + border-bottom: none; +} + +tr:hover { + background: #f8f8f8; + transition: background 0.15s ease; +} + +tr:nth-child(even) { + background: #fafafa; +} + +tr:nth-child(even):hover { + background: #f5f5f5; +} + +/* запретить justify внутри таблиц */ +table, +table th, +table td { + text-align: left !important; // переопределяем возможный глобальный justify + text-align-last: auto; // чтобы последняя строка не дотягивалась + text-justify: auto; // отменяем межсловное выравнивание + hyphens: manual; // без агрессивных переносов + word-break: normal; + white-space: normal; +} + +/* на случай, если в ячейках есть p/span/a с унаследованным justify */ +table :is(p, span, a, li) { + text-align: left !important; } .list { &-post-title { - margin-bottom: .25rem; + margin-bottom: 0.25rem; a { - color: #333; - &:hover, &:focus { text-decoration: none; @@ -267,7 +369,7 @@ tbody tr:nth-child(odd) th { } &-post-date { margin-bottom: 1rem; - font-size: .75rem; + font-size: $font-size-small; text-transform: uppercase; } } @@ -275,10 +377,18 @@ tbody tr:nth-child(odd) th { // customization .list-header { margin: auto; - padding: 5px; + padding: 1rem 0; } -.list-header>h3 { +.list-header > h1 { + margin: auto; +} + +.list-header > h2 { + margin: auto; +} + +.list-header > h3 { margin: auto; } @@ -288,13 +398,41 @@ tbody tr:nth-child(odd) th { } .list-post-title .name { - font-size: 18px; + font-size: $font-size-name; + text-decoration: none; +} + +.list-item a:hover, +.list-post-title:hover .name, +.list-post-title .name:hover { + color: $href-color; +} + +.data-table > summary { + display: flex; + align-items: center; + cursor: pointer; + list-style: none; + outline: none; } -.list-post-title { - color: black; +.data-table > summary::before { + content: ""; + display: inline-block; + width: 0; + height: 0; + border-top: 0.5em solid transparent; + border-bottom: 0.5em solid transparent; + border-left: 0.6em solid #333; + margin-right: 0.7em; + transition: transform 0.2s; } -.list-item a:hover, .list-post-title:hover .name, .list-post-title .name:hover { - color: #c42929; -} \ No newline at end of file +.data-table[open] > summary::before { + transform: rotate(90deg); +} + +.data-table > summary h3 { + margin: 0.5rem 0; + font-size: $font-size-h3; +} diff --git a/_sass/_mixins.scss b/_sass/_mixins.scss new file mode 100644 index 00000000..e5c40594 --- /dev/null +++ b/_sass/_mixins.scss @@ -0,0 +1,75 @@ +// Миксины для переиспользования +@mixin respond-to($breakpoint) { + @if $breakpoint == mobile { + @media (max-width: #{$lt-width - 1px}) { + @content; + } + } + @if $breakpoint == tablet { + @media (min-width: $lt-width) and (max-width: #{$md-width - 1px}) { + @content; + } + } + @if $breakpoint == desktop { + @media (min-width: $md-width) { + @content; + } + } + @if $breakpoint == large { + @media (min-width: $lg-width) { + @content; + } + } +} + +@mixin button-base { + display: inline-block; + padding: 0.75rem 1.5rem; + border: none; + border-radius: 0.5rem; + font-family: $font-family-base; + font-weight: $font-weight-medium; + text-decoration: none; + cursor: pointer; + transition: all 0.2s ease; + + &:hover, + &:focus { + transform: translateY(-2px); + box-shadow: 0 4px 20px $shadow-medium; + } +} + +@mixin card-shadow { + box-shadow: 0 2px 12px $shadow-light; + transition: box-shadow 0.2s ease; + + &:hover, + &:focus { + box-shadow: 0 4px 20px $shadow-medium; + } +} + +@mixin flex-center { + display: flex; + align-items: center; + justify-content: center; +} + +@mixin text-truncate { + overflow: hidden; + text-overflow: ellipsis; + white-space: nowrap; +} + +@mixin visually-hidden { + position: absolute !important; + width: 1px !important; + height: 1px !important; + padding: 0 !important; + margin: -1px !important; + overflow: hidden !important; + clip: rect(0, 0, 0, 0) !important; + white-space: nowrap !important; + border: 0 !important; +} diff --git a/_sass/_navbar.scss b/_sass/_navbar.scss index e8628b45..019aa250 100644 --- a/_sass/_navbar.scss +++ b/_sass/_navbar.scss @@ -1,33 +1,54 @@ // Навигация по сайт (сверху) .navbar-page { - height: 50px; - margin-bottom: 0px; + height: 48px; + margin: auto auto; width: 100%; } .navbar-container { + font-family: $font-primary; height: 100%; width: 100%; padding-right: 15px; padding-left: 15px; margin-right: auto; margin-left: auto; + border-bottom: 2px solid #f5f5f5; } @media (min-width: $lt-width) { .navbar-right { - float: right!important; + float: right !important; margin-right: 0px; } - + + .navbar-center { + float: none; + margin: 0 auto; + text-align: center; + } + + .navbar-center > li { + float: none; + display: inline-block; + } + .navbar-container { width: 100%; } } +@media (max-width: $md-width) { + .navbar-page { + height: 30px; + } +} + @media (min-width: $md-width) { .navbar-container { width: 100%; + padding-left: 15px; + padding-right: 15px; } } @@ -56,7 +77,6 @@ } .navbar-brand { - font-size: 20px; font-weight: 300; padding: 0px; } @@ -66,65 +86,441 @@ margin-bottom: 0px; } -.navbar, .navbar-nav>li>a { - background-color: $bg-navbar; - font-family: 'Open Sans', sans-serif; - text-transform: uppercase; +.navbar, +.navbar-nav > li > a { + text-decoration: none; + background-color: $bg-default; font-weight: 400; - font-size: 80%; + font-size: $font-size-navbar; + // padding: 15px; + color: #333; + transition: color 0.3s ease; +} + +.navbar-nav > li > a:hover, +.navbar-nav > li > a:focus { + color: $href-color !important; + background-color: $bg-default !important; +} + +// Специфичность для ссылок с классом name +.navbar-nav > li > a.name { + color: #333; + text-decoration: none; +} + +.navbar-nav > li > a.name:hover, +.navbar-nav > li > a.name:focus { + color: $href-color !important; + background-color: $bg-default !important; +} + +// Стили для dropdown (Materials и т.д.) +.navbar-nav > li > a.dropdown-toggle { + color: #333; + text-decoration: none; +} + +.navbar-nav > li > a.dropdown-toggle:hover, +.navbar-nav > li > a.dropdown-toggle:focus { + color: $href-color !important; + background-color: $bg-default !important; +} + +// Стили для выпадающего меню в основной навигации +.navbar-nav > li.dropdown { + position: relative; + + .dropdown-menu { + background-color: $bg-default; + border: 1px solid #ddd; + border-radius: 4px; + box-shadow: 0 2px 8px rgba(0, 0, 0, 0.1); + padding: 0; + margin-top: 0; + min-width: 200px; + + ul { + list-style: none; + padding: 0; + margin: 0; + + li { + width: 100%; + border-bottom: 1px solid #f0f0f0; + + &:last-child { + border-bottom: none; + } + + a { + display: block; + padding: 8px 20px; + color: #333; + text-decoration: none; + font-size: $font-size-navbar; + font-weight: 400; + transition: all 0.2s ease; + + &:hover, + &:focus { + background-color: #f8f8f8; + color: $href-color; + } + } + } + } + } } -.navbar-nav>li { +.navbar-nav > li { margin-bottom: 0; - padding: 0px; + padding: 3px; } -.navbar-toggle, .navbar-default .navbar-toggle:hover { +.navbar-toggle, +.navbar-default, +.navbar-toggle:hover { border: none; - background-color: $bg-navbar; + background-color: $bg-default; margin-left: auto; margin-right: auto; } -// Навигация по странице (слева) +.navbar-toggle { + .icon-bar { + background-color: #333; + transition: background-color 0.3s ease; + } + + &:hover .icon-bar, + &:focus .icon-bar { + background-color: $href-color; + } +} + +.navbar-social-block { + display: flex; + align-items: center; + gap: 1.1rem; + margin-left: auto; + padding-right: 15px; + + .social-link { + color: #333; + text-decoration: none; + display: flex; + align-items: center; + transition: opacity 0.3s ease; + + &:hover, + &:focus { + color: $href-color; + } + + img { + height: 24px; + width: 24px; + display: block; + } + } +} + +.navbar-container { + display: grid; + grid-template-columns: 1fr auto 1fr; + align-items: center; + width: 100%; + max-width: 100%; + + .navbar-header { + justify-self: start; // логотип слева + min-width: 0; // Позволяет сжиматься + } + + .navbar-collapse { + justify-self: center; // меню точно по центру + min-width: 0; // Позволяет сжиматься + } + + .navbar-social-block { + justify-self: end; // соцсети справа + min-width: fit-content; // Не позволяет сжиматься + } +} + +.navbar-social-block { + display: flex; + align-items: center; + gap: 1rem; + padding-right: 0; + + .nav-item.dropdown { + display: flex; + align-items: center; + + .nav-link { + padding: 10px 12px; + font-size: $font-size-navbar; + font-weight: 400; + color: #333 !important; + text-decoration: none; + transition: color 0.3s ease; + cursor: pointer; + + &:hover, + &:focus { + color: $href-color !important; + text-decoration: none; + } + } + + // Стили для выпадающего меню + .dropdown-menu { + background-color: $bg-default; + border: 1px solid #ddd; + border-radius: 4px; + box-shadow: 0 2px 8px rgba(0, 0, 0, 0.1); + padding: 0; + margin-top: 5px; + min-width: 70px; + right: 0; + left: auto; + + ul { + list-style: none; + padding: 0; + margin: 0; + + li { + width: 100%; + border-bottom: 1px solid #f0f0f0; -div.section-nav { + &:last-child { + border-bottom: none; + } + + a { + display: block; + padding: 8px 15px; + color: #333; + text-decoration: none; + font-size: $font-size-navbar; + font-weight: 400; + transition: all 0.2s ease; + text-align: center; + + &:hover, + &:focus { + background-color: #f8f8f8; + color: $href-color; + } + } + } + } + } + + // При наведении на сам dropdown показываем красный цвет + &:hover .nav-link, + &.open .nav-link { + color: $href-color !important; + } + } +} + +a.navbar-social { + color: inherit; + font-size: $font-size-navbar-icon; + text-decoration: none; display: flex; + align-items: center; + transition: opacity 0.3s ease; } -ul.section-nav { - margin: auto; - text-align: left; - list-style-type: none; - padding: 10px; +// Убедитесь, что collapse не имеет float +.navbar-collapse { + float: none; } -.toc-entry>ul > li::before { - display: inline-block; - content: "-"; - width: 1em; - text-align: center; - margin-left: -1em; +// Мобильный соц-блок - скрыт по умолчанию (для десктопа) +.navbar-social-mobile { + display: none; } -ul.section-nav > li::before { - display: inline-block; - content: "-"; - width: 1em; - text-align: center; - margin-left: -1em; + +@media (max-width: $md-width) { + .navbar-brand { + display: none !important; + } + .navbar-social-block { + display: none !important; + } } -.toc-entry>ul { - list-style-type: none; +// Для мобильных - единый блок всех стилей +@media (max-width: $lt-width) { + // Основные стили navbar + .navbar { + min-height: auto; + padding: 0; + } + + .navbar-toggle { + padding: 10px 10px; + margin: 0; + } + + // Скрываем десктопный соц-блок + .navbar-social-block { + display: none; + } + + // Убираем ограничения для Bootstrap collapse + .collapse { + max-height: none !important; + overflow: visible !important; + } + + .collapse.in { + overflow: visible !important; + } + + // Отключаем анимацию для быстрого появления меню + .navbar-collapse.collapsing { + transition: none !important; + height: auto !important; + } + + .navbar-container { + grid-template-columns: 1fr; + justify-content: center; + padding: 0; + min-height: auto; + + .navbar-header { + justify-self: stretch; + width: 100%; + display: flex; + justify-content: flex-end; + align-items: center; + padding: 5px 15px; + + // Скрываем логотип на мобильных + .navbar-brand { + display: none; + } + + // Кнопка toggle справа с симметричными отступами + .navbar-toggle { + margin: 0; + padding: 8px 8px; + float: none; + } + } + .navbar-collapse { + grid-column: 1; + justify-self: stretch; + width: 100%; + max-height: none !important; + overflow: visible !important; + + // Меню по левому краю на мобильных + .navbar-center { + text-align: left; + + > li { + display: block; + width: 100%; + padding: 0 5px; + margin: 0; + + > a { + display: block; + width: 100%; + padding: 10px 10px; + border-bottom: 1px solid #f0f0f0; + } + } + } + } + + .navbar-social-block { + display: none !important; + } + } + + // Показываем мобильную версию соц-блока только на мобильных + .navbar-social-mobile { + display: block !important; + padding: 0; + margin-left: 0; + margin-top: 0px; + + .navbar-social-mobile-divider { + height: 1px; + background: #fafafa; + margin-bottom: 10px; + } + + .navbar-social-mobile-item { + margin-bottom: 10px; + + .navbar-social-mobile-label { + display: block; + font-family: $font-primary; + margin-bottom: 6px; + } + + .navbar-social-mobile-links { + display: flex; + gap: 12px; + + a { + color: #333; + text-decoration: none; + font-size: 0.95rem; + font-weight: 400; + padding: 4px 8px; + transition: all 0.2s ease; + + &.active { + background-color: $href-color; + color: white; + } + + &:hover, + &:focus { + color: $href-color; + background-color: white; + } + + &.active:hover { + background-color: darken($href-color, 10%); + color: white; + } + } + } + + .navbar-social-mobile-icons { + gap: 15px; + + a { + text-decoration: none; + color: #333; + font-size: 1.3rem; + transition: color 0.2s ease; + + &:hover, + &:focus { + color: $href-color; + } + } + } + } + } } -.toc-entry>a { - color: inherit; - font-size: 12px; - - &:hover, - &:focus { - text-decoration: none; - text-shadow: 0px 0px 4px; +@media (max-width: 1365px) { + .navbar-logo-ru { + display: none !important; } -} \ No newline at end of file +} diff --git a/_sass/_page.scss b/_sass/_page.scss index b5fd0ad9..4c81a2ed 100644 --- a/_sass/_page.scss +++ b/_sass/_page.scss @@ -1,20 +1,43 @@ .container { - width: 100%; - padding: 0px; + width: 100%; + padding: 0px; } .content { padding: 10px; - margin-left: auto; - margin-right: auto; - text-align: justify; + margin-top: 2rem !important; + margin-bottom: 3rem !important; + margin-left: auto !important; + margin-right: auto !important; min-height: 100vh; + + &.content--home { + margin-top: 0 !important; + } +} + +@media (max-width: $md-width) { + .container { + width: 100%; + padding: 0 10px; + } + + .content { + margin-left: 0; + margin-right: 0; + width: 100%; + + &.content--home { + margin-left: 0; + margin-right: 0; + } + } } -.sidebar-left { - display: flex; - overflow-y: scroll; - background-color: $bg-sidecar; +@media (max-width: $lt-width) { + .content { + margin-top: 1rem !important; + } } @media (min-width: $lt-width) { @@ -23,15 +46,13 @@ } .content { - margin-left: calc(#{$page-margin}*100%); + margin-left: calc(#{$page-margin}* 100%); width: calc(#{$lt-width} * 0.7); - } - .sidebar-left { - position: fixed; - top: 50px; - bottom: 0px; - width: calc(#{$lt-width} * #{$page-margin}); + &.content--home { + margin-left: auto; + margin-right: auto; + } } } @@ -41,15 +62,13 @@ } .content { - margin-left: calc(#{$page-margin}*100%); + margin-left: calc(#{$page-margin}* 100%); width: 70%; - } - .sidebar-left { - position: fixed; - top: 50px; - bottom: 0px; - width: calc(#{$page-margin}*100%); + &.content--home { + margin-left: auto; + margin-right: auto; + } } } @@ -59,15 +78,13 @@ } .content { - margin-left: calc(#{$page-margin}*100%); + // margin-left: calc(#{$page-margin}* 100%); width: calc(#{$lg-width} * 0.7); - } - .sidebar-left { - position: fixed; - top: 50px; - bottom: 0px; - width: calc(#{$lg-width} * #{$page-margin}); + &.content--home { + margin-left: auto; + margin-right: auto; + } } } @@ -77,15 +94,13 @@ } .content { - margin-left: calc(#{$page-margin}*100%); + margin-left: calc(#{$page-margin}* 100%); width: calc(#{$xl-width} * 0.7); - } - .sidebar-left { - position: fixed; - top: 50px; - bottom: 0px; - width: calc(#{$xl-width} * #{$page-margin}); + &.content--home { + margin-left: auto; + margin-right: auto; + } } } @@ -95,15 +110,13 @@ } .content { - margin-left: calc(#{$page-margin}*100%); + margin-left: calc(#{$page-margin}* 100%); width: calc(#{$qhd-width} * 0.7); - } - .sidebar-left { - position: fixed; - top: 50px; - bottom: 0px; - width: calc(#{$qhd-width} * #{$page-margin}); + &.content--home { + margin-left: auto; + margin-right: auto; + } } } @@ -113,14 +126,12 @@ } .content { - margin-left: calc(#{$page-margin}*100%); + margin-left: calc(#{$page-margin}* 100%); width: calc(#{$wqhd-width} * 0.7); - } - .sidebar-left { - position: fixed; - top: 50px; - bottom: 0px; - width: calc(#{$wqhd-width} * #{$page-margin}); + &.content--home { + margin-left: auto; + margin-right: auto; + } } -} \ No newline at end of file +} diff --git a/_sass/_profile.scss b/_sass/_profile.scss index ca5627bb..802f8605 100644 --- a/_sass/_profile.scss +++ b/_sass/_profile.scss @@ -6,17 +6,187 @@ } .list-post-title { - width: 150px; + width: 150px; + margin: 0 auto; + display: flex; + flex-direction: column; + align-items: center; + text-align: center; + gap: 0rem; } .people { margin: auto; text-align: center; margin-top: 0.75em; + display: flex; + flex-wrap: wrap; + justify-content: center; + gap: 0rem; } .list-item-people { - display: inline-flex; - padding: 5px; + display: flex; + flex-direction: column; + align-items: center; + padding: 0; width: 220px; } + +@media (max-width: $sm-width) { + .list-item-people { + width: 150px; + } + + .list-post-title { + width: 120px; + } + + .profile-thumbnail { + width: 100px; + height: 100px; + } +} + +// Стили для страницы профиля +.profile-header { + display: flex; + align-items: flex-start; + gap: 30px; + margin-bottom: 30px; + flex-wrap: wrap; + + .profile-avatar { + flex-shrink: 0; + + img { + border-radius: 0.5rem; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + } + } + + .profile-info { + flex: 1; + min-width: 300px; + } +} + +@media (max-width: $sm-width) { + .profile-header { + gap: 0; + } + .profile-avatar { + flex-shrink: 0; + + img { + width: 200px; + height: auto; + } + } +} + +// Блок с контактными ссылками +.profile-links { + font-family: $font-primary; + font-size: $font-size-name; + display: inline-block; + padding: 7px 20px; + margin-bottom: 10px; + margin-top: 10px; + border-radius: 1rem; + border-left: 10px solid #f5f5f5; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + text-decoration: none; + + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; + + &:hover, + &:focus { + background-color: #f5f5f5; + text-decoration: none; + } + + .profile-link-item { + display: block; + font-size: $font-size-name; + margin: 10px 0; + text-decoration: none; + transition: color 0.3s ease; + + i { + margin-right: 10px; + width: 20px; + display: inline-block; + text-align: center; + } + + a { + text-decoration: none; + transition: color 0.3s ease; + + &:hover, + &:focus { + color: $href-color; + } + } + + &:first-child { + margin-top: 0; + } + + &:last-child { + margin-bottom: 0; + } + } +} + +// Список курсов в стиле карточек +.profile-courses-list { + display: block; + flex-direction: column; + + .profile-course-item { + font-family: $font-primary; + font-size: $font-size-name; + display: block; + border-radius: 1rem; + padding: 0.75rem; + margin: 0.25rem 0; + border-left: 10px solid #f5f5f5; + background-color: #fff; + box-shadow: + 0px 1px 3px rgba(0, 0, 0, 0.05), + 1px 0px 3px rgba(0, 0, 0, 0.05); + text-decoration: none; + + transition: + box-shadow 0.2s, + transform 0.2s, + background-color 0.2s; + + &:hover, + &:focus { + background-color: #f5f5f5; + cursor: pointer; + } + } +} + +@media (max-width: 768px) { + .profile-header { + flex-direction: column; + align-items: center; + text-align: center; + + .profile-info { + min-width: auto; + } + } +} diff --git a/_sass/_sidecar.scss b/_sass/_sidecar.scss deleted file mode 100644 index ee0332a0..00000000 --- a/_sass/_sidecar.scss +++ /dev/null @@ -1,78 +0,0 @@ -.masthead { - text-align: center; - margin: auto; - margin-top: 0px; - width: 100%; - padding: 10px; -} - -.avatar-image { - width: 30%; - height: auto; - border-radius: 50%; - display: block; - margin-right: auto; - margin-left: auto; -} - -.masthead-title { - padding: 0; - margin: 0; - font-size: 1rem; - font-weight: 400; - - a:hover, - a:focus { - color: var(--link-hover-color); - } -} - -.masthead-tagline { - padding: 0; - margin: 0; - font-size: 1.25rem; - font-weight: 400; - opacity: .7; -} - -.navigation-list { - margin-top: var(--spacer-2); - padding: 0; - list-style: none; -} - -.navigation-item { - display: block; - margin-bottom: var(--spacer); -} - -.navigation-item a { - background: transparent; - color: inherit; - letter-spacing: 0.05em; - font-size: 90%; - border-bottom: 2px solid; - border-color: inherit; - - &:hover, - &:focus { - color: var(--link-hover-color); - } -} - -a.social { - color: inherit; - font-size: 50px; - margin: 10px; - - &:hover, - &:focus { - text-decoration: none; - text-shadow: 0px 0px 4px; - } -} - -.separator { - text-align: center; - padding: 0px 5px; -} \ No newline at end of file diff --git a/_sass/_toc.scss b/_sass/_toc.scss new file mode 100644 index 00000000..ab28ea0c --- /dev/null +++ b/_sass/_toc.scss @@ -0,0 +1,202 @@ +.toc { + position: fixed; + font-size: 0.9rem; + top: 96px; + right: 32px; + width: min(280px, 80vw); + max-height: calc(100vh - 144px); + padding: 0; + margin: 0; + background: rgba(255, 255, 255, 0.95); + border-radius: 1rem; + border-left: 10px solid #eaeaea; + box-shadow: + 0px 3px 5px rgba(0, 0, 0, 0.05), + 3px 0px 5px rgba(0, 0, 0, 0.05); + overflow: hidden; + opacity: 0; + visibility: hidden; + transform: translate3d(0, -12px, 0) scale(0.98); + transition: + opacity 400ms cubic-bezier(0.16, 1, 0.3, 1), + transform 500ms cubic-bezier(0.16, 1, 0.3, 1), + visibility 400ms ease; + z-index: 1400; + + &.is-visible { + opacity: 1; + visibility: visible; + transform: translate3d(0, 0, 0) scale(1); + } + + &.is-pinned { + opacity: 1; + visibility: visible; + } + + &[hidden] { + display: none; + } + + .toc__container { + display: flex; + flex-direction: column; + height: 100%; + } + + .toc__header { + display: flex; + align-items: center; + gap: 0.85rem; + padding: 16px 20px 10px; + border-bottom: 1px solid #eaeaea; + } + + .toc__title { + font-size: 0.9rem; + font-weight: 600; + margin: 0; + letter-spacing: 0.02em; + } + + .toc__body { + font-size: 0.9rem; + position: relative; + padding: 12px 20px 20px; + max-height: clamp(320px, 56vh, 560px); + overflow: hidden auto; + scrollbar-gutter: stable both-edges; + } + + .toc__list { + list-style: none; + margin: 0; + padding: 0; + display: grid; + gap: 0.3rem; + } + + .toc__list ul { + list-style: none; + margin: 0.35rem 0 0.3rem 0.9rem; + padding-left: 0.6rem; + border-left: 1px solid #eaeaea; + } + + .toc__link { + display: inline-flex; + align-items: center; + font-size: 0.9rem; + gap: 0.4rem; + padding: 4px 6px; + border-radius: 6px; + text-decoration: none; + line-height: 1.4; + transition: + color 140ms ease, + background 140ms ease; + + &::before { + content: ""; + display: inline-block; + width: 6px; + height: 6px; + border-radius: 50%; + background: currentColor; + opacity: 0.12; + transition: + opacity 140ms ease, + transform 140ms ease; + } + } + + .toc__link--level-3 { + color: #bbbbbb; + } + + .toc__link--level-4 { + color: #bbbbbb; + } + + .toc__link--active { + color: #333; + &::before { + opacity: 1; + transform: scale(1.4); + } + } + + .toc__empty { + color: #eaeaea; + margin: 0; + padding: 16px 0; + } + + &.has-scroll { + .toc__body { + mask-image: linear-gradient( + to bottom, + rgba(0, 0, 0, 0.85) 0%, + rgba(0, 0, 0, 1) 24px, + rgba(0, 0, 0, 1) calc(100% - 24px), + rgba(0, 0, 0, 0.2) 100% + ); + } + + .toc__body::after, + .toc__body::before { + content: ""; + position: sticky; + left: 0; + right: 0; + height: 12px; + pointer-events: none; + z-index: 2; + } + + .toc__body::before { + top: 0; + background: linear-gradient(to bottom, rgba(255, 255, 255, 0.94), rgba(255, 255, 255, 0)); + } + + .toc__body::after { + bottom: 0; + background: linear-gradient(to top, rgba(255, 255, 255, 0.94), rgba(255, 255, 255, 0)); + } + } + + .toc__body { + &::-webkit-scrollbar { + width: 10px; + } + + &::-webkit-scrollbar-track { + background: transparent; + } + + &::-webkit-scrollbar-thumb { + background: #eaeaea; + border-radius: 999px; + } + } +} + +[data-toc-content] { + scroll-padding-top: 120px; + + h2, + h3, + h4 { + scroll-margin-top: 120px; + } +} + +@media (prefers-reduced-motion: reduce) { + .toc { + transition: none; + + .toc__link::before { + transition: none; + } + } +} diff --git a/_sass/_variables.scss b/_sass/_variables.scss index 74c50922..6c1598da 100644 --- a/_sass/_variables.scss +++ b/_sass/_variables.scss @@ -8,7 +8,37 @@ $wqhd-width: 3440px; $uhd-width: 3840px; $bg-default: #fff; -$bg-sidecar: #fafafa; -$bg-navbar: #fafafa; +$href-color: #c42929; +$href-bg-color: #ffeeee; -$page-margin: 0.3 \ No newline at end of file +$page-margin: 0.3; + +// Font families +$font-primary: "Open Sans", sans-serif; +$font-monospace: ui-monospace, Monaco, monospace; + +// Fonts +$font-size-base: 18px; +$font-weight-base: 400; + +$font-size-base-large: 1rem; + +// Headings +$font-size-h1: 2rem; +$font-size-h2: 1.6rem; +$font-size-h3: 1.3rem; +$font-size-h4: 1.1rem; + +// Content +$font-size-body: 1rem; +$font-size-small: 0.8rem; +$font-size-name: 1rem; +$font-size-code: 1rem; + +// UI elements +$font-size-navbar: 1rem; +$font-size-navbar-icon: 24px; +$font-size-footer-icon: 20px; + +// Math display +$font-size-math: 1rem; diff --git a/about.md b/about.md deleted file mode 100755 index 7d6cf3e7..00000000 --- a/about.md +++ /dev/null @@ -1,9 +0,0 @@ ---- -title: titles.about -edit: true -permalink: /about/ -meta_desc_en: "Department of Intelligent Systems, Phystech School of Applied Mathematics and Informatics." -meta_desc_ru: "Кафедра интеллектуальных систем. Физтех-школа прикладной математики и информатики" ---- - -{% tf about.md %} diff --git a/admission.md b/admission.md index 9cf7cc34..8f730f4e 100644 --- a/admission.md +++ b/admission.md @@ -2,7 +2,7 @@ title: titles.admission edit: true permalink: /admission/ -meta_desc_en: "The admission to Master's and Bachelor programme at the Department of Intelligence systems" +meta_desc_en: "The admission to Master's and Bachelor programme at the Department of Intelligence systems" meta_desc_ru: "Поступление в бакалавриат и магистратуру Кафедры интеллектуальных систем" --- diff --git a/conferences.md b/conferences.md index eb5a5ff0..16ce10c6 100755 --- a/conferences.md +++ b/conferences.md @@ -2,8 +2,10 @@ title: titles.conferences edit: true permalink: /materials/conferences/ -meta_desc_en: "Department of Intelligent Systems, conferences list info" +meta_desc_en: "Department of Intelligent Systems, conferences list info" meta_desc_ru: "Кафедра интеллектуальных систем, информация о конференциях по специальности" +toc: true +toc_headings: h3, h4 --- {% tf conferences.md %} diff --git a/course.md b/course.md index 2cd4c007..4c017494 100755 --- a/course.md +++ b/course.md @@ -1,26 +1,26 @@ --- title: titles.course permalink: /course/ -meta_desc_en: "Department of Intelligent Systems, academical courses at the Bachelor and Maste programme" +meta_desc_en: "Department of Intelligent Systems, academical courses at the Bachelor and Maste programme" meta_desc_ru: "Кафедра интеллектуальных систем, курсы бакалавриата и магистратуры" --- {% for type in site.global.course.types %}
-

{% t site.global.course.types.{{ type }} %}

+

{% t site.global.course.types.{{ type }} %}

-
+
{% for course in site.course %} {% if course.type contains type %} - -
-

- {% t courses.name.{{ course.id | split: "/" | last }} %} -

-
- + +
+

+ {% t courses.{{ course.id | split: "/" | last }} %} +

+
+ {% endif %} {% endfor %}
diff --git a/docker_test.sh b/docker_test.sh deleted file mode 100644 index 3ee93dbd..00000000 --- a/docker_test.sh +++ /dev/null @@ -1,3 +0,0 @@ -# this is an extremely ineffective one-liner for testing our site -docker run --rm -it -v $(pwd):/data -p 4000:4000 -e LANG=C.UTF-8 -it ubuntu:20.04 /bin/bash -c "cd /data; apt-get update; apt-get install -y bundler; bundle install; bundle exec jekyll serve --host 0.0.0.0" - diff --git a/images/.DS_Store b/images/.DS_Store index 23b14750..0d8dbf4c 100644 Binary files a/images/.DS_Store and b/images/.DS_Store differ diff --git a/images/course/deep-learning-audio.jpg b/images/course/deep-learning-audio.jpg new file mode 100644 index 00000000..24ca6c3d Binary files /dev/null and b/images/course/deep-learning-audio.jpg differ diff --git a/images/course/deep-learning.jpg b/images/course/deep-learning.jpg new file mode 100644 index 00000000..17b72e8a Binary files /dev/null and b/images/course/deep-learning.jpg differ diff --git a/images/course/default.jpg b/images/course/default.jpg deleted file mode 100755 index 47c72872..00000000 Binary files a/images/course/default.jpg and /dev/null differ diff --git a/images/course/default.svg b/images/course/default.svg new file mode 100644 index 00000000..1bfbc485 --- /dev/null +++ b/images/course/default.svg @@ -0,0 +1,24 @@ + + + + + + + + + \ No newline at end of file diff --git a/images/life/bachelors-2024.jpeg b/images/life/bachelors-2024.jpeg new file mode 100644 index 00000000..9663732c Binary files /dev/null and b/images/life/bachelors-2024.jpeg differ diff --git a/images/life/bachelors-2025.jpeg b/images/life/bachelors-2025.jpeg new file mode 100644 index 00000000..2d4338d1 Binary files /dev/null and b/images/life/bachelors-2025.jpeg differ diff --git a/images/life/masters-2024.jpeg b/images/life/masters-2024.jpeg new file mode 100644 index 00000000..acdffb77 Binary files /dev/null and b/images/life/masters-2024.jpeg differ diff --git a/images/life/masters-2025.jpeg b/images/life/masters-2025.jpeg new file mode 100644 index 00000000..6f02adec Binary files /dev/null and b/images/life/masters-2025.jpeg differ diff --git a/images/logo/.!2384!logo_square.jpg b/images/logo/.!2384!logo_square.jpg deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2385!apple-icon-144x144.png b/images/logo/.!2385!apple-icon-144x144.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2386!apple-icon-precomposed.png b/images/logo/.!2386!apple-icon-precomposed.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2387!apple-icon-114x114.png b/images/logo/.!2387!apple-icon-114x114.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2388!apple-icon-72x72.png b/images/logo/.!2388!apple-icon-72x72.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2642!logo_square.jpg b/images/logo/.!2642!logo_square.jpg deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2645!apple-icon-144x144.png b/images/logo/.!2645!apple-icon-144x144.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2646!apple-icon-precomposed.png b/images/logo/.!2646!apple-icon-precomposed.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2647!apple-icon-114x114.png b/images/logo/.!2647!apple-icon-114x114.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!2650!apple-icon-72x72.png b/images/logo/.!2650!apple-icon-72x72.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!3233!logo_square.jpg b/images/logo/.!3233!logo_square.jpg deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!3237!apple-icon-144x144.png b/images/logo/.!3237!apple-icon-144x144.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!3240!apple-icon-precomposed.png b/images/logo/.!3240!apple-icon-precomposed.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!3241!apple-icon-114x114.png b/images/logo/.!3241!apple-icon-114x114.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/.!3250!apple-icon-72x72.png b/images/logo/.!3250!apple-icon-72x72.png deleted file mode 100755 index e69de29b..00000000 diff --git a/images/logo/apple-icon-114x114.png b/images/logo/apple-icon-114x114.png deleted file mode 100755 index 100342af..00000000 Binary files a/images/logo/apple-icon-114x114.png and /dev/null differ diff --git a/images/logo/apple-icon-144x144.png b/images/logo/apple-icon-144x144.png deleted file mode 100755 index 100342af..00000000 Binary files a/images/logo/apple-icon-144x144.png and /dev/null differ diff --git a/images/logo/apple-icon-72x72.png b/images/logo/apple-icon-72x72.png deleted file mode 100755 index 100342af..00000000 Binary files a/images/logo/apple-icon-72x72.png and /dev/null differ diff --git a/images/logo/apple-icon-precomposed.png b/images/logo/apple-icon-precomposed.png deleted file mode 100755 index 100342af..00000000 Binary files a/images/logo/apple-icon-precomposed.png and /dev/null differ diff --git a/images/logo/apple-touch-icon.png b/images/logo/apple-touch-icon.png new file mode 100644 index 00000000..7408afc4 Binary files /dev/null and b/images/logo/apple-touch-icon.png differ diff --git a/images/logo/email.svg b/images/logo/email.svg new file mode 100644 index 00000000..63896df7 --- /dev/null +++ b/images/logo/email.svg @@ -0,0 +1 @@ +1-Email \ No newline at end of file diff --git a/images/logo/favicon.ico b/images/logo/favicon.ico new file mode 100644 index 00000000..160953b4 Binary files /dev/null and b/images/logo/favicon.ico differ diff --git a/images/logo/github.svg b/images/logo/github.svg new file mode 100644 index 00000000..37fa923d --- /dev/null +++ b/images/logo/github.svg @@ -0,0 +1 @@ + \ No newline at end of file diff --git a/images/logo/icon-16.png b/images/logo/icon-16.png new file mode 100644 index 00000000..fa5e5a71 Binary files /dev/null and b/images/logo/icon-16.png differ diff --git a/images/logo/icon-192.png b/images/logo/icon-192.png new file mode 100644 index 00000000..0585ca9f Binary files /dev/null and b/images/logo/icon-192.png differ diff --git a/images/logo/icon-32.png b/images/logo/icon-32.png new file mode 100644 index 00000000..7792173f Binary files /dev/null and b/images/logo/icon-32.png differ diff --git a/images/logo/icon-48.png b/images/logo/icon-48.png new file mode 100644 index 00000000..f97b40c3 Binary files /dev/null and b/images/logo/icon-48.png differ diff --git a/images/logo/icon-512.png b/images/logo/icon-512.png new file mode 100644 index 00000000..79e369c2 Binary files /dev/null and b/images/logo/icon-512.png differ diff --git a/images/logo/logo-full.png b/images/logo/logo-full.png new file mode 100644 index 00000000..f4a97f63 Binary files /dev/null and b/images/logo/logo-full.png differ diff --git a/images/logo/logo-square.png b/images/logo/logo-square.png new file mode 100644 index 00000000..f7894f70 Binary files /dev/null and b/images/logo/logo-square.png differ diff --git a/images/logo/logo_square.jpg b/images/logo/logo_square.jpg deleted file mode 100755 index 100342af..00000000 Binary files a/images/logo/logo_square.jpg and /dev/null differ diff --git a/images/logo/rutube.svg b/images/logo/rutube.svg new file mode 100644 index 00000000..ccda175a --- /dev/null +++ b/images/logo/rutube.svg @@ -0,0 +1,12 @@ + + + + + + + + + + + + diff --git a/images/logo/telegram.svg b/images/logo/telegram.svg new file mode 100644 index 00000000..4481033e --- /dev/null +++ b/images/logo/telegram.svg @@ -0,0 +1,18 @@ + + + + + + + + + + + + + diff --git a/images/logo/youtube.svg b/images/logo/youtube.svg new file mode 100644 index 00000000..c49a5ad8 --- /dev/null +++ b/images/logo/youtube.svg @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/images/main/landing-bg.jpg b/images/main/landing-bg.jpg new file mode 100644 index 00000000..0f054f82 Binary files /dev/null and b/images/main/landing-bg.jpg differ diff --git a/images/main/landing-bg_original.jpg b/images/main/landing-bg_original.jpg new file mode 100644 index 00000000..0e0d30e0 Binary files /dev/null and b/images/main/landing-bg_original.jpg differ diff --git a/images/main/students.jpg b/images/main/students.jpg new file mode 100644 index 00000000..7d8f2fbf Binary files /dev/null and b/images/main/students.jpg differ diff --git a/images/main/students.png b/images/main/students.png new file mode 100644 index 00000000..6477e168 Binary files /dev/null and b/images/main/students.png differ diff --git a/images/main/students_original.png b/images/main/students_original.png new file mode 100644 index 00000000..6477e168 Binary files /dev/null and b/images/main/students_original.png differ diff --git a/images/main/zhuravlev_rudakov_merged.jpg b/images/main/zhuravlev_rudakov_merged.jpg new file mode 100644 index 00000000..fda03593 Binary files /dev/null and b/images/main/zhuravlev_rudakov_merged.jpg differ diff --git a/images/main/zhuravlev_rudakov_merged.png b/images/main/zhuravlev_rudakov_merged.png new file mode 100644 index 00000000..1dd4530f Binary files /dev/null and b/images/main/zhuravlev_rudakov_merged.png differ diff --git a/images/main/zhuravlev_rudakov_merged_original.png b/images/main/zhuravlev_rudakov_merged_original.png new file mode 100644 index 00000000..1dd4530f Binary files /dev/null and b/images/main/zhuravlev_rudakov_merged_original.png differ diff --git "a/images/main/\320\262\321\206_\321\200\320\260\320\275.jpg" "b/images/main/\320\262\321\206_\321\200\320\260\320\275.jpg" new file mode 100644 index 00000000..b55935f2 Binary files /dev/null and "b/images/main/\320\262\321\206_\321\200\320\260\320\275.jpg" differ diff --git "a/images/main/\320\262\321\206_\321\200\320\260\320\275_original.jpg" "b/images/main/\320\262\321\206_\321\200\320\260\320\275_original.jpg" new file mode 100644 index 00000000..f780a12c Binary files /dev/null and "b/images/main/\320\262\321\206_\321\200\320\260\320\275_original.jpg" differ diff --git a/images/people/bishuk_ay.jpeg b/images/people/bishuk_ay.jpeg index be301f1c..b024aa2b 100644 Binary files a/images/people/bishuk_ay.jpeg and b/images/people/bishuk_ay.jpeg differ diff --git a/images/people/default.jpg b/images/people/default.jpg old mode 100755 new mode 100644 diff --git a/images/people/dorin_dd.jpeg b/images/people/dorin_dd.jpeg new file mode 100644 index 00000000..4723a104 Binary files /dev/null and b/images/people/dorin_dd.jpeg differ diff --git a/images/people/firsov_sa.jpg b/images/people/firsov_sa.jpg new file mode 100644 index 00000000..78431b69 Binary files /dev/null and b/images/people/firsov_sa.jpg differ diff --git a/images/people/isachenko_rv.jpg b/images/people/isachenko_rv.jpg index be4fe92e..a97796b4 100644 Binary files a/images/people/isachenko_rv.jpg and b/images/people/isachenko_rv.jpg differ diff --git a/images/people/kasyuk_va.jpeg b/images/people/kasyuk_va.jpeg new file mode 100644 index 00000000..d2ac613b Binary files /dev/null and b/images/people/kasyuk_va.jpeg differ diff --git a/images/people/kiselev_ns.jpg b/images/people/kiselev_ns.jpg new file mode 100644 index 00000000..61006169 Binary files /dev/null and b/images/people/kiselev_ns.jpg differ diff --git a/images/people/kreinin_mv.jpeg b/images/people/kreinin_mv.jpeg new file mode 100644 index 00000000..b91072ad Binary files /dev/null and b/images/people/kreinin_mv.jpeg differ diff --git a/images/people/morozov_ma.jpg b/images/people/morozov_ma.jpg new file mode 100644 index 00000000..b0d078ed Binary files /dev/null and b/images/people/morozov_ma.jpg differ diff --git a/images/people/nikitina_ma.jpeg b/images/people/nikitina_ma.jpeg new file mode 100644 index 00000000..a13063e7 Binary files /dev/null and b/images/people/nikitina_ma.jpeg differ diff --git a/images/people/noname.jpg b/images/people/noname.jpg deleted file mode 100644 index d5783d2e..00000000 Binary files a/images/people/noname.jpg and /dev/null differ diff --git a/images/people/panchenko_sk.jpg b/images/people/panchenko_sk.jpg new file mode 100644 index 00000000..036e079d Binary files /dev/null and b/images/people/panchenko_sk.jpg differ diff --git a/images/people/severilov_pa.jpg b/images/people/severilov_pa.jpg index 35c478ce..32b847ba 100644 Binary files a/images/people/severilov_pa.jpg and b/images/people/severilov_pa.jpg differ diff --git a/images/people/tikhonov_dm.jpeg b/images/people/tikhonov_dm.jpeg new file mode 100644 index 00000000..dd24f253 Binary files /dev/null and b/images/people/tikhonov_dm.jpeg differ diff --git a/images/people/vladimirov_ea.jpeg b/images/people/vladimirov_ea.jpeg new file mode 100644 index 00000000..27d28b7a Binary files /dev/null and b/images/people/vladimirov_ea.jpeg differ diff --git a/images/people/yakovlev_kd.jpg b/images/people/yakovlev_kd.jpg new file mode 100644 index 00000000..ddb5bafd Binary files /dev/null and b/images/people/yakovlev_kd.jpg differ diff --git a/index.md b/index.md index e8c7b478..f2779e21 100755 --- a/index.md +++ b/index.md @@ -1,11 +1,10 @@ --- -layout: page +layout: default title: titles.index -edit: true permalink: / -image: /images/main/main.jpg -meta_desc_en: "Department of Intelligent Systems, schedule and announcements" -meta_desc_ru: "Кафедра интеллектуальных систем, расписание и объявления" +home: true +meta_desc_en: "Department of Intelligent Systems at MIPT - training bachelors and masters in applied mathematics and physics with focus on data science, ML and AI" +meta_desc_ru: "Кафедра интеллектуальных систем МФТИ - подготовка бакалавров и магистров по прикладной математике и физике с фокусом на анализ данных, машинное обучение и ИИ" --- {% tf index.md %} diff --git a/javascript/carousel.js b/javascript/carousel.js new file mode 100644 index 00000000..287ad249 --- /dev/null +++ b/javascript/carousel.js @@ -0,0 +1,22 @@ +document.addEventListener('DOMContentLoaded', function() { + // Проверяем, существует ли элемент карусели на странице + const carouselElement = document.querySelector('#carousel-demo'); + + if (carouselElement) { + // Инициализируем карусель без динамической загрузки CSS + bulmaCarousel.attach('#carousel-demo', { + slidesToScroll: 1, + slidesToShow: 1, + autoplay: true, + autoplaySpeed: 5000, + loop: true, + pagination: false, + navigation: true, + navigationSwipe: true, + breakpoints: [ + { changePoint: 768, slidesToShow: 1, slidesToScroll: 1 }, + { changePoint: 1024, slidesToShow: 1, slidesToScroll: 1 } + ] + }); + } +}); \ No newline at end of file diff --git a/javascript/copy_email.js b/javascript/copy_email.js new file mode 100644 index 00000000..33e627d6 --- /dev/null +++ b/javascript/copy_email.js @@ -0,0 +1,50 @@ +// Function to copy email to clipboard and show tooltip +function copyEmailToClipboard(event, email) { + event.preventDefault(); + + // Detect language from page + const isRussian = document.documentElement.lang === 'ru' || window.location.pathname.includes('/ru/'); + const message = isRussian ? 'Скопировано в буфер обмена!' : 'Copied to clipboard!'; + + // Copy to clipboard + navigator.clipboard.writeText(email).then(function() { + // Create tooltip element + const tooltip = document.createElement('div'); + tooltip.textContent = message; + tooltip.style.cssText = ` + position: fixed; + left: ${event.clientX}px; + top: ${event.clientY - 40}px; + background-color: #333; + color: white; + padding: 8px 12px; + border-radius: 6px; + font-family: "Open Sans", sans-serif; + font-size: 14px; + z-index: 10000; + pointer-events: none; + opacity: 0; + transition: opacity 0.3s ease; + box-shadow: 0 2px 8px rgba(0,0,0,0.2); + `; + + document.body.appendChild(tooltip); + + // Fade in + setTimeout(() => { + tooltip.style.opacity = '1'; + }, 10); + + // Fade out and remove + setTimeout(() => { + tooltip.style.opacity = '0'; + setTimeout(() => { + document.body.removeChild(tooltip); + }, 300); + }, 2000); + }).catch(function(err) { + console.error('Failed to copy email: ', err); + }); + + return false; +} diff --git a/javascript/fade_in.js b/javascript/fade_in.js new file mode 100644 index 00000000..36929e91 --- /dev/null +++ b/javascript/fade_in.js @@ -0,0 +1,81 @@ +// Fade-in on scroll effect using Intersection Observer +(function() { + 'use strict'; + + // Page fade-in on load + function initPageFadeIn() { + // Check if user prefers reduced motion + const prefersReducedMotion = window.matchMedia('(prefers-reduced-motion: reduce)').matches; + + if (prefersReducedMotion) { + // Skip animation for users who prefer reduced motion + document.body.classList.add('page-loaded'); + } else { + // Add class after a tiny delay to ensure styles are loaded + requestAnimationFrame(function() { + document.body.classList.add('page-loaded'); + }); + } + } + + // Force scroll to top on page load/refresh + if ('scrollRestoration' in history) { + history.scrollRestoration = 'manual'; + } + + // Configuration + const config = { + threshold: 0.1, // Элемент должен быть виден хотя бы на 10% + rootMargin: '0px 0px -100px 0px' // Триггер за 100px до края экрана + }; + + // Create observer + const observer = new IntersectionObserver(function(entries) { + entries.forEach(function(entry) { + if (entry.isIntersecting) { + // Add visible class when element is in viewport + entry.target.classList.add('visible'); + // Stop observing this element + observer.unobserve(entry.target); + } + }); + }, config); + + // Observe all elements with fade-in classes + function initFadeIn() { + const selectors = [ + '.fade-in-section', + '.fade-in-left', + '.fade-in-right', + '.fade-in-up', + '.fade-in-down', + '.fade-in-scale' + ]; + + selectors.forEach(function(selector) { + const elements = document.querySelectorAll(selector); + elements.forEach(function(element) { + observer.observe(element); + }); + }); + } + + // Initialize when DOM is ready + if (document.readyState === 'loading') { + document.addEventListener('DOMContentLoaded', function() { + initPageFadeIn(); + initFadeIn(); + }); + } else { + initPageFadeIn(); + initFadeIn(); + } + + // Scroll to top after page is fully loaded (including images and styles) + window.addEventListener('load', function() { + // Small delay to ensure all layout shifts are complete + setTimeout(function() { + window.scrollTo(0, 0); + }, 0); + }); +})(); diff --git a/javascript/mermaid_init.js b/javascript/mermaid_init.js new file mode 100644 index 00000000..212cbb3d --- /dev/null +++ b/javascript/mermaid_init.js @@ -0,0 +1,38 @@ +// Mermaid initialization module +import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs'; + +mermaid.initialize({ + startOnLoad: false, + theme: 'base' +}); + +// Wait for DOM to be ready +if (document.readyState === 'loading') { + document.addEventListener('DOMContentLoaded', initMermaid); +} else { + initMermaid(); +} + +async function initMermaid() { + // Find all mermaid code blocks + const mermaidBlocks = document.querySelectorAll('pre > code.language-mermaid, .language-mermaid'); + + mermaidBlocks.forEach((block, index) => { + // Create a div for mermaid to render into + const mermaidDiv = document.createElement('div'); + mermaidDiv.className = 'mermaid'; + mermaidDiv.textContent = block.textContent; + + // Replace the code block with the mermaid div + if (block.parentElement.tagName === 'PRE') { + block.parentElement.replaceWith(mermaidDiv); + } else { + block.replaceWith(mermaidDiv); + } + }); + + // Run mermaid on all .mermaid divs + await mermaid.run({ + querySelector: '.mermaid' + }); +} diff --git a/javascript/table_scroll.js b/javascript/table_scroll.js new file mode 100644 index 00000000..735ed540 --- /dev/null +++ b/javascript/table_scroll.js @@ -0,0 +1,23 @@ +document.addEventListener('DOMContentLoaded', () => { + const tables = document.querySelectorAll('table'); + + tables.forEach((table) => { + if (table.closest('.table-scroll') || table.dataset.noScroll === 'true') { + return; + } + + const wrapper = document.createElement('div'); + wrapper.className = 'table-scroll'; + wrapper.tabIndex = 0; + wrapper.setAttribute('role', 'region'); + + const ariaLabel = table.getAttribute('aria-label') + || table.querySelector('caption')?.textContent + || 'Scrollable data table'; + + wrapper.setAttribute('aria-label', ariaLabel.trim()); + + table.parentNode?.insertBefore(wrapper, table); + wrapper.appendChild(table); + }); +}); diff --git a/javascript/toc.js b/javascript/toc.js new file mode 100644 index 00000000..984d26c5 --- /dev/null +++ b/javascript/toc.js @@ -0,0 +1,413 @@ +const parseNumber = (value, fallback) => { + const parsed = Number.parseInt(value, 10); + return Number.isFinite(parsed) ? parsed : fallback; +}; + +const tocRoot = document.querySelector('[data-toc]'); + +if (tocRoot) { + const config = { + scrollThreshold: parseNumber(tocRoot.dataset.scrollThreshold, 0), + hideDelay: parseNumber(tocRoot.dataset.hideDelay, 1600), + headingSelector: tocRoot.dataset.headingSelector || 'h2,h3', + tocDepth: parseNumber(tocRoot.dataset.tocDepth, null), + sticky: tocRoot.dataset.tocSticky === 'true', + contentSelector: tocRoot.dataset.tocContentSelector || '[data-toc-content]', + velocityDistance: Math.max(parseNumber(tocRoot.dataset.velocityDistance, 360), 24), + velocityWindow: Math.max(parseNumber(tocRoot.dataset.velocityWindow, 480), 120) + }; + + const contentRoot = document.querySelector(config.contentSelector); + + if (!contentRoot) { + tocRoot.remove(); + // eslint-disable-next-line no-console + console.warn('[toc] content container not found for selector', config.contentSelector); + } else { + const headings = collectHeadings(contentRoot, config.headingSelector, config.tocDepth); + + if (!headings.length) { + renderEmptyMessage(tocRoot); + tocRoot.hidden = false; + } else { + assignMissingIds(headings); + buildTocList(tocRoot, headings); + applyScrollableState(tocRoot); + bindBehaviour(tocRoot, headings, config); + tocRoot.hidden = false; + } + } +} + +function collectHeadings(root, selector, depthLimit) { + const selectors = selector + .split(',') + .map((item) => item.trim().toLowerCase()) + .filter(Boolean); + + if (!selectors.length) { + return []; + } + + const rawHeadings = Array.from(root.querySelectorAll(selectors.join(','))); + + const validHeadings = rawHeadings.filter((heading) => { + if (heading.dataset.tocSkip === 'true') { + return false; + } + const level = extractHeadingLevel(heading); + if (!Number.isFinite(level)) { + return false; + } + + const text = heading.dataset.tocLabel || heading.textContent; + if (!text || !text.trim()) { + return false; + } + + return true; + }); + + if (!validHeadings.length) { + return []; + } + + const baseLevel = validHeadings.reduce((carry, heading) => Math.min(carry, extractHeadingLevel(heading)), Infinity); + const maxDepth = Number.isInteger(depthLimit) ? baseLevel + depthLimit - 1 : Infinity; + + return validHeadings.filter((heading) => extractHeadingLevel(heading) <= maxDepth); +} + +function renderEmptyMessage(tocElement) { + const body = tocElement.querySelector('[data-toc-body]'); + if (!body) { + return; + } + + const message = document.createElement('p'); + message.className = 'toc__empty'; + message.textContent = tocElement.getAttribute('aria-label') || 'Contents'; + body.innerHTML = ''; + body.appendChild(message); +} + +function assignMissingIds(headings) { + const slugMap = new Map(); + + headings.forEach((heading) => { + if (heading.id) { + return; + } + + const base = slugify(heading.dataset.tocLabel || heading.textContent.trim()); + const count = slugMap.get(base) || 0; + slugMap.set(base, count + 1); + heading.id = count === 0 ? base : `${base}-${count + 1}`; + }); +} + +function slugify(text) { + return text + .toLowerCase() + .normalize('NFD') + .replace(/[\u0300-\u036f]/g, '') + .replace(/[^a-z0-9\s-]/g, '') + .trim() + .replace(/[\s_-]+/g, '-'); +} + +function buildTocList(tocElement, headings) { + const listRoot = tocElement.querySelector('[data-toc-list]'); + if (!listRoot) { + return; + } + + listRoot.innerHTML = ''; + const baseLevel = headings.reduce((minLevel, heading) => Math.min(minLevel, extractHeadingLevel(heading)), Infinity); + let currentLevel = baseLevel; + let currentList = listRoot; + const listStack = [listRoot]; + let previousLevel = baseLevel; + + headings.forEach((heading) => { + const rawLevel = Math.max(extractHeadingLevel(heading), baseLevel); + let level = rawLevel; + + if (level > previousLevel + 1) { + level = previousLevel + 1; + } + + if (level > currentLevel) { + for (let i = currentLevel; i < level; i += 1) { + const parentItem = currentList.lastElementChild; + if (!parentItem) { + break; + } + const nestedList = document.createElement('ul'); + parentItem.appendChild(nestedList); + currentList = nestedList; + listStack.push(currentList); + } + } else if (level < currentLevel) { + const stepsUp = Math.min(listStack.length - 1, currentLevel - level); + for (let i = 0; i < stepsUp; i += 1) { + listStack.pop(); + } + currentList = listStack[listStack.length - 1] || listRoot; + } + + currentLevel = level; + previousLevel = level; + + const listItem = document.createElement('li'); + const link = document.createElement('a'); + const label = heading.dataset.tocLabel || heading.textContent.trim(); + link.className = `toc__link toc__link--level-${level}`; + link.href = `#${heading.id}`; + link.textContent = label; + link.setAttribute('data-toc-target', heading.id); + listItem.appendChild(link); + currentList.appendChild(listItem); + }); +} + +function bindBehaviour(tocElement, headings, cfg) { + const links = Array.from(tocElement.querySelectorAll('[data-toc-target]')); + if (!links.length) { + return; + } + + const headingsById = new Map(headings.map((heading) => [heading.id, heading])); + let hideTimer = null; + let visible = cfg.sticky; + let lastScrollTop = window.scrollY || window.pageYOffset; + let lastScrollTime = performance.now(); + let lastDirection = 0; + let burstDistance = 0; + let burstStartTime = lastScrollTime; + const minDistance = cfg.velocityDistance; + const windowMs = cfg.velocityWindow; + + const clearHideTimer = () => { + if (hideTimer) { + window.clearTimeout(hideTimer); + hideTimer = null; + } + }; + + const hideToc = () => { + if (cfg.sticky) { + return; + } + clearHideTimer(); + tocElement.classList.remove('is-visible'); + visible = false; + }; + + const scheduleHide = () => { + if (cfg.sticky) { + return; + } + clearHideTimer(); + hideTimer = window.setTimeout(hideToc, cfg.hideDelay); + }; + + const showToc = () => { + if (!visible) { + tocElement.classList.add('is-visible'); + visible = true; + } + }; + + const updateActiveLink = () => { + const activeId = detectActiveHeading(headings); + links.forEach((link) => { + const isActive = link.dataset.tocTarget === activeId; + link.classList.toggle('toc__link--active', isActive); + if (isActive) { + link.setAttribute('aria-current', 'true'); + } else { + link.removeAttribute('aria-current'); + } + }); + }; + + const resetActiveLinks = () => { + links.forEach((link) => { + link.classList.remove('toc__link--active'); + link.removeAttribute('aria-current'); + }); + }; + + const onScroll = throttle(() => { + const scrollTop = window.scrollY || window.pageYOffset; + const now = performance.now(); + const delta = scrollTop - lastScrollTop; + let direction = delta === 0 ? 0 : delta > 0 ? 1 : -1; + + if (direction === 0) { + if (now - burstStartTime > windowMs) { + burstDistance = 0; + lastDirection = 0; + } + } else if (direction !== lastDirection || now - burstStartTime > windowMs) { + burstDistance = Math.abs(delta); + burstStartTime = now; + lastDirection = direction; + } else { + burstDistance += Math.abs(delta); + } + + const burstDuration = now - burstStartTime; + const passedThreshold = scrollTop > cfg.scrollThreshold || direction < 0; + const quickBurst = + direction !== 0 && burstDistance >= minDistance && burstDuration <= windowMs && passedThreshold; + + if (quickBurst) { + showToc(); + scheduleHide(); + updateActiveLink(); + burstDistance = 0; + burstStartTime = now; + lastDirection = 0; + direction = 0; + } else if (!cfg.sticky && scrollTop <= cfg.scrollThreshold) { + hideToc(); + resetActiveLinks(); + } else if (visible) { + updateActiveLink(); + } + + lastDirection = direction; + lastScrollTop = scrollTop; + lastScrollTime = now; + }); + + window.addEventListener('scroll', onScroll, { passive: true }); + + const onResize = throttle(() => { + updateActiveLink(); + applyScrollableState(tocElement); + }, 120); + + window.addEventListener('resize', onResize); + + tocElement.addEventListener('mouseenter', () => { + showToc(); + clearHideTimer(); + updateActiveLink(); + }); + + tocElement.addEventListener('focusin', () => { + showToc(); + clearHideTimer(); + updateActiveLink(); + }); + + tocElement.addEventListener('mouseleave', scheduleHide); + tocElement.addEventListener('focusout', (event) => { + if (!tocElement.contains(event.relatedTarget)) { + scheduleHide(); + } + }); + + links.forEach((link) => { + link.addEventListener('click', (event) => { + const targetId = link.dataset.tocTarget; + const targetHeading = headingsById.get(targetId); + if (!targetHeading) { + return; + } + + event.preventDefault(); + const smooth = window.matchMedia('(prefers-reduced-motion: no-preference)').matches; + targetHeading.scrollIntoView({ + behavior: smooth ? 'smooth' : 'auto', + block: 'start' + }); + updateActiveLink(); + scheduleHide(); + }); + }); + + if (cfg.sticky) { + tocElement.classList.add('is-pinned'); + updateActiveLink(); + } else { + onScroll(); + } + + const body = tocElement.querySelector('[data-toc-body]'); + if (body && typeof ResizeObserver !== 'undefined') { + const observer = new ResizeObserver(() => applyScrollableState(tocElement)); + observer.observe(body); + } +} + +function detectActiveHeading(headings) { + const viewportHeight = window.innerHeight || document.documentElement.clientHeight; + let bestId = null; + let bestVisibility = 0; + + headings.forEach((heading) => { + const rect = heading.getBoundingClientRect(); + if (rect.bottom <= 0 || rect.top >= viewportHeight) { + return; + } + + const visibleTop = Math.max(rect.top, 0); + const visibleBottom = Math.min(rect.bottom, viewportHeight); + const visibleHeight = Math.max(0, visibleBottom - visibleTop); + const visibilityRatio = visibleHeight / Math.max(rect.height, 1); + + if (visibilityRatio > bestVisibility) { + bestVisibility = visibilityRatio; + bestId = heading.id; + } + }); + + if (bestId) { + return bestId; + } + + const scrollTop = window.scrollY || window.pageYOffset; + for (let index = headings.length - 1; index >= 0; index -= 1) { + if (headings[index].offsetTop <= scrollTop + 80) { + return headings[index].id; + } + } + + return headings[0]?.id || null; +} + +function extractHeadingLevel(heading) { + const match = /H(\d)/.exec(heading.tagName); + return match ? Number.parseInt(match[1], 10) : NaN; +} + +function throttle(callback, wait = 80) { + let ticking = false; + let lastArgs = []; + + return function throttled(...args) { + lastArgs = args; + if (!ticking) { + window.requestAnimationFrame(() => { + callback.apply(this, lastArgs); + ticking = false; + }); + ticking = true; + } + }; +} + +function applyScrollableState(tocElement) { + const body = tocElement.querySelector('[data-toc-body]'); + if (!body) { + return; + } + + const epsilon = 4; + const hasScroll = body.scrollHeight - body.clientHeight > epsilon; + tocElement.classList.toggle('has-scroll', hasScroll); +} diff --git a/nir.md b/nir.md index f6489ad6..e1c2ef99 100755 --- a/nir.md +++ b/nir.md @@ -2,8 +2,10 @@ title: titles.nir edit: true permalink: /materials/nir/ -meta_desc_en: "Department of Intelligent Systems, scientific reports" +meta_desc_en: "Department of Intelligent Systems, scientific reports" meta_desc_ru: "Кафедра интеллектуальных систем, отчеты по проделанной научной работе, НИР" +toc: true +toc_headings: h2, h3 --- {% tf nir.md %} diff --git a/people.md b/people.md index 158695e9..edeae0ed 100755 --- a/people.md +++ b/people.md @@ -1,29 +1,29 @@ --- title: titles.people permalink: /people/ -meta_desc_en: "Lecturers at the Department of Intelligent Systems: Founders of the Department, Doctors of Science, Ph.D, teachers, Graduate Students, Instructors" +meta_desc_en: "Lecturers at the Department of Intelligent Systems: Founders of the Department, Doctors of Science, PhD, teachers, Graduate Students, Instructors" meta_desc_ru: "Преподаватели Кафедры интеллектуальных систем: Основатели кафедры, Доктора наук, Кандидаты наук, преподаватели, Аспиранты, семинаристы" --- -{% for role in site.global.people.roles %} +{% for role in site.global.people.roles %} {% if role != 'template' %}
-

{% t site.global.people.roles.{{ role }} %}

+

{% t site.global.people.roles.{{ role }} %}

-
+
{% for profile in site.people %} - {% if profile.position contains role %} + {% if profile.position == role %}

{% if profile.avatar %} - + {% else %} - + {% endif %} - {% t peoples.name.{{ profile.id | split: "/" | last }} %} + {% t people.{{ profile.id | split: "/" | last }} %}

{% endif %} diff --git a/style.scss b/style.scss index 7db51be3..78180548 100755 --- a/style.scss +++ b/style.scss @@ -2,11 +2,14 @@ --- @import "variables"; +@import "mixins"; +@import "fade_in"; +@import "home"; @import "navbar"; @import "footer"; @import "page"; @import "profile"; -@import "profile"; @import "course"; +@import "admission"; @import "main"; -@import "sidecar"; +@import "toc"; diff --git a/templates.md b/templates.md new file mode 100755 index 00000000..6b83437e --- /dev/null +++ b/templates.md @@ -0,0 +1,9 @@ +--- +title: titles.templates +edit: true +permalink: /materials/templates/ +meta_desc_en: "Department of Intelligent Systems, templates info" +meta_desc_ru: "Кафедра интеллектуальных систем, информация о шаблонах" +--- + +{% tf templates.md %} diff --git a/thesis.md b/thesis.md index 83901fd8..92c4e0c3 100755 --- a/thesis.md +++ b/thesis.md @@ -2,8 +2,10 @@ title: titles.thesis edit: true permalink: /materials/thesis/ -meta_desc_en: "Department of Intelligent Systems, Student theses" +meta_desc_en: "Department of Intelligent Systems, Student theses" meta_desc_ru: "Кафедра интеллектуальных систем. ВКР студентов" +toc: true +toc_headings: h3, h4 --- {% tf thesis.md %}