-
Notifications
You must be signed in to change notification settings - Fork 4
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
2d69186
commit 675c9de
Showing
20 changed files
with
224 additions
and
142 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,33 @@ | ||
# Blogs | ||
|
||
[Lil'Log](https://lilianweng.github.io/lil-log/) - Lilian Weng | ||
|
||
[Deep Learning: Our Miraculous Year 1990-1991 - Jürgen Schmidhuber (2019)](http://people.idsia.ch/~juergen/deep-learning-miraculous-year-1990-1991.html) | ||
|
||
[Berkeley Artifical Intelligence Research - BAIR](https://bair.berkeley.edu/blog/) | ||
- [When Recurrent Models Don't Need to be Recurrent](https://bair.berkeley.edu/blog/2018/08/06/recurrent/) | ||
|
||
[lossfunctions](https://lossfunctions.tumblr.com/) | ||
|
||
[colah's blog](https://colah.github.io/) | ||
- [Visual Information Theory](https://colah.github.io/posts/2015-09-Visual-Information/) | ||
- [Understanding LSTM Networks](https://colah.github.io/posts/2015-08-Understanding-LSTMs/) | ||
|
||
[Berkeley Artifical Intelligence Research (BAIR)](https://bair.berkeley.edu/blog/) | ||
|
||
Andrej Karpathy - [gitpages blog](http://karpathy.github.io/) - [medium](https://medium.com/@karpathy) | ||
- [A Recipe for Training Neural Networks](http://karpathy.github.io/2019/04/25/recipe/) | ||
- [Software 2.0](https://medium.com/@karpathy/software-2-0-a64152b37c35) | ||
- [Yes you should understand backprop](https://medium.com/@karpathy/yes-you-should-understand-backprop-e2f06eab496b) | ||
- [A Recipe for Training Neural Networks](https://karpathy.github.io/2019/04/25/recipe/) | ||
|
||
[Jürgen Schmidhuber](http://people.idsia.ch/~juergen/) | ||
- [Deep Learning: Our Miraculous Year 1990-1991](http://people.idsia.ch/~juergen/deep-learning-miraculous-year-1990-1991.html) | ||
|
||
[Off The Convex Path](http://www.offconvex.org/) | ||
- [When Recurrent Models Don't Need to be Recurrent](http://www.offconvex.org/2018/07/27/approximating-recurrent/) - the trade-offs between recurrent and feed-forward models | ||
|
||
[Import AI - Jack Clark](https://jack-clark.net/) | ||
|
||
[inconvergent](https://inconvergent.net/) | ||
- [On Generative Algorithms](https://inconvergent.net/generative/) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,41 @@ | ||
# Books and Articles | ||
|
||
*Stuff to read* | ||
|
||
[Paperclip maximizer](https://wiki.lesswrong.com/wiki/Paperclip_maximizer) | ||
|
||
## Non-technical overviews | ||
|
||
[How computers got shockingly good at recognizing images - Ars Technica](https://arstechnica.com/science/2018/12/how-computers-got-shockingly-good-at-recognizing-images/) | ||
|
||
[The basics of modern AI—how does it work and will it destroy society this year? - Ars Technica](https://arstechnica.com/features/2019/04/from-ml-to-gan-to-hal-a-peak-behind-the-modern-artificial-intelligence-curtain/) | ||
|
||
[Dairy farming, solar panels, and diagnosing Parkinson's disease: what can you do with deep learning? - fast.ai](https://www.fast.ai/2019/02/21/dl-projects/) | ||
|
||
[The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World (2015 book) - Pedro Domingos](https://en.wikipedia.org/wiki/The_Master_Algorithm) | ||
|
||
[Algorithms to Live By: The Computer Science of Human Decisions - Christian & Griffiths](https://www.goodreads.com/book/show/25666050-algorithms-to-live-by) | ||
|
||
[Superintelligence: Paths, Dangers, Strategies (2014 book) - Nick Bostrom](https://en.wikipedia.org/wiki/Superintelligence:_Paths,_Dangers,_Strategies) | ||
|
||
[How Not to Be Wrong: The Power of Mathematical Thinking - Jordan Ellenberg](https://en.wikipedia.org/wiki/How_Not_to_Be_Wrong) | ||
|
||
[Statistics Done Wrong - Alex Reinhart](https://www.statisticsdonewrong.com/) | ||
|
||
## Criticism | ||
|
||
[2018 - The rise of 'pseudo-AI': how tech firms quietly use humans to do bots' work](https://www.theguardian.com/technology/2018/jul/06/artificial-intelligence-ai-humans-bots-tech-companies) | ||
|
||
[2018 - Artificial intelligence: winter is coming - Financial Times](https://www.ft.com/content/47111fce-d0a4-11e8-9a3c-5d5eac8f1ab4) | ||
|
||
[2018 - What worries me about AI – François Chollet](https://medium.com/@francois.chollet/what-worries-me-about-ai-ed9df072b704) | ||
|
||
[2019 - Our Entire AI Revolution Is Built On A Correlation House Of Cards - Forbes](https://www.forbes.com/sites/kalevleetaru/2019/04/20/our-entire-ai-revolution-is-built-on-a-correlation-house-of-cards/#22c051a54969) | ||
|
||
[2019 - Machine learning systems are stuck in a rut](https://blog.acolyer.org/2019/06/28/machine-learning-systems-are-stuck-in-a-rut/) | ||
|
||
[2019 - DeepMind's losses and the future of artificial intelligence - WIRED](https://www.wired.com/story/deepminds-losses-future-artificial-intelligence/) | ||
|
||
## Domain specific | ||
|
||
[The financial world wants to open AI's boxes – MIT Technology Review](https://www.technologyreview.com/s/604122/the-financial-world-wants-to-open-ais-black-boxes/) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1,3 @@ | ||
[CS231n: Convolutional Neural Networks for Visual Recognition](http://cs231n.stanford.edu/) | ||
|
||
Feature Visualization - How neural networks build up their understanding of images - [distill](https://distill.pub/2017/feature-visualization/) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,33 @@ | ||
# Courses | ||
|
||
Bay Area Deep Learning School | ||
|
||
[Day One](https://www.youtube.com/watch?v=eyovmAtoUx0) | ||
|
||
- [Deep Learning - Hugo Larochelle](https://youtu.be/eyovmAtoUx0?list=WL&t=585) | ||
- [Vision - Andrej Karpathy](https://youtu.be/eyovmAtoUx0?list=WL&t=5266) | ||
- [NLP - Richard Socher](https://youtu.be/eyovmAtoUx0?t=14036) | ||
- [Unsupervised - Ruslan Salakhutdinov](https://youtu.be/eyovmAtoUx0?list=WL&t=25874) | ||
|
||
[Day Two](https://www.youtube.com/watch?v=9dXiAecyJrY) | ||
|
||
- [Reinforcement Learning - John Schulman](https://youtu.be/9dXiAecyJrY?t=361) | ||
- [Theano - Pascal Lamblin](https://youtu.be/9dXiAecyJrY?t=6702) | ||
- [Speech recognition - Adam Coates](https://youtu.be/9dXiAecyJrY?t=13878) | ||
- [Torch - Alex Wiltschko](https://youtu.be/9dXiAecyJrY?t=20966) | ||
- [Sequences - Quoc Lee](https://youtu.be/9dXiAecyJrY?t=25463) | ||
- [Foundations & Challenges - Yoshua Bengio](https://youtu.be/9dXiAecyJrY?t=30704) | ||
|
||
Full Stack Deep Learning - [Course homepage](https://course.fullstackdeeplearning.com/) - [March 2019 videos](https://fullstackdeeplearning.com/march2019) | ||
- [Lecture 3: Jeremy Howard](https://www.youtube.com/watch?v=hZd3X_nGdew) | ||
- [Lecture 8: Troubleshooting Deep Neural Networks - Josh Tobin](https://www.youtube.com/watch?v=GwGTwPcG0YM) | ||
- [Lecture 9: Testing and Deployment - Sergey Karayev](https://www.youtube.com/watch?v=nu7h1zdKPd0) | ||
|
||
[End-to-End Machine Learning](https://end-to-end-machine-learning.teachable.com/) | ||
|
||
[DeepMind x UCL | Deep Learning Lecture Series 2020](https://www.youtube.com/playlist?list=PLqYmG7hTraZCDxZ44o4p3N5Anz3lLRVZF) | ||
- [1 - Intro - Thore Graepel](https://youtu.be/7R52wiUgxZI) | ||
- [2 - Neural Network Foundations - Wojciech Czarnecki](https://youtu.be/FBggC-XVF4://youtu.be/FBggC-XVF4M) | ||
- [3 - Convolution - Sander Dieleman](https://youtu.be/shVKhOmT0H://youtu.be/shVKhOmT0HE) | ||
- [6 - Sequences and Recurrent Networks - Marta Garnelo](https://youtu.be/87kLfzmYBy8) | ||
- [11 - Modern Latent Variable Models - Andriy Mnih](https://youtu.be/7Pcvdo4EJeo) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,3 +1,7 @@ | ||
[What is wrong with convolutional neural nets? - Geoffrey Hinton - Fields Institute, 2017](https://www.youtube.com/watch?v=Mqt8fs6ZbHk) | ||
|
||
[This AI startup claims to automate app making but actually just uses humans](https://www.theverge.com/2019/8/14/20805676/engineer-ai-artificial-intelligence-startup-app-development-outsourcing-humans) | ||
|
||
[The rise of 'pseudo-AI': how tech firms quietly use humans to do bots' work](https://www.theguardian.com/technology/2018/jul/06/artificial-intelligence-ai-humans-bots-tech-companies) | ||
|
||
[An understanding of AI’s limitations is starting to sink in](https://www.economist.com/technology-quarterly/2020/06/11/an-understanding-of-ais-limitations-is-starting-to-sink-in) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,25 @@ | ||
# Podcasts | ||
|
||
[Lex Fridman - AI Podcast](https://www.youtube.com/playlist?list=PLrAXtmErZgOdP_8GztsuKi9nrraNbKKp4) | ||
|
||
- [Juergen Schmidhuber](https://www.youtube.com/watch?v=3FIo6evmweo&t=0s) | ||
- [Pieter Abbeel](https://www.youtube.com/watch?v=l-mYLq6eZPY&t=0s) | ||
- [Oriol Vinyals](https://www.youtube.com/watch?v=Kedt2or9xlo) | ||
- [Ian Goodfellow](https://www.youtube.com/watch?v=Z6rxFNMGdn0) | ||
- [Guido van Rossum](https://www.youtube.com/watch?v=ghwaIiE3Nd8) | ||
- [George Hotz](https://www.youtube.com/watch?v=iwcYp-XT7UI) | ||
- [Yann LeCun](https://www.youtube.com/watch?v=SGSOCuByo24) | ||
- [Jeremy Howard - fastai](https://www.youtube.com/watch?v=J6XcP4JOHmk) | ||
- [Greg Brockman - OpenAI](https://www.youtube.com/watch?v=bIrEM2FbOLU) | ||
- [Yoshua Bengio](https://www.youtube.com/watch?v=azOmzumh0vQ) | ||
- [François Chollet - Keras](https://www.youtube.com/watch?v=Bo8MY4JpiXE) | ||
- [Grant Sanderson - 3Blue1Brown](https://www.youtube.com/watch?v=U_lKUK2MCsg) | ||
- [Andrew Ng](https://youtu.be/0jspaMLxBig) | ||
- [David Silver](https://www.youtube.com/watch?v=uPUEq8d73JI) | ||
- [Ilya Sutskever](https://youtu.be/13CZPWmke6A) | ||
|
||
[Talking Machines](http://www.thetalkingmachines.com/) | ||
- [The Deep End of Deep Learning](http://www.thetalkingmachines.com/episodes/deep-end-deep-learning?context_entity_type=node&context_entity_id=29216) | ||
- | ||
This Week in AI | ||
- [Are We Being Honest About How Difficult AI Really Is? with David Ferrucc](https://twimlai.com/twiml-talk-268-are-we-being-honest-about-how-difficult-ai-really-is-with-david-ferrucci/) |
Oops, something went wrong.