Skip to content
A community run, 5-day PyTorch Deep Learning Bootcamp
Branch: master
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
.idea Add files via upload Dec 25, 2017
Kaggle-PyTorch tuned params for senet Jan 22, 2018
PDF Delete 01_15.pdf Jul 25, 2017
cpp-11 CUDNN 6 Sep 30, 2017
day01 update sample solution Nov 5, 2017
day02-PyTORCH-and-PyCUDA Add files via upload Nov 28, 2017
day03 rl for real for real Nov 9, 2017
day04 Add files via upload Nov 7, 2017
day05 Added Yam's stuff. Nov 9, 2017
docker Update Jan 10, 2018
.gitignore Initial commit Jul 19, 2017
LICENSE Initial commit Jul 19, 2017 Update Sep 7, 2017
bootcamp.jpg Add files via upload Aug 21, 2017
curr.png Add files via upload Sep 7, 2017
image085.jpg Add files via upload Jul 23, 2017 CUDNN 6 Sep 30, 2017 Update Jul 30, 2017

Deep Learning Winter School, November 2107.

Tel Aviv Deep Learning Bootcamp :



Tel-Aviv Deep Learning Bootcamp is an intensive (and free!) 5-day program intended to teach you all about deep learning. It is nonprofit focused on advancing data science education and fostering entrepreneurship. The Bootcamp is a prominent venue for graduate students, researchers, and data science professionals. It offers a chance to study the essential and innovative aspects of deep learning.

Participation is via a donation to the A.L.S ASSOCIATION for promoting research of the Amyotrophic Lateral Sclerosis (ALS) disease.


The Bootcamp amalgamates “Theory” and “Practice” – identifying that a deep learning scientist desires a survey of concepts combined with a strong application of practical techniques through labs. Primarily, the foundational material and tools of the Data Science practitioner are presented via Sk-Learn. Topics continue rapidly into exploratory data analysis and classical machine learning, where the data is organized, characterized, and manipulated. From day two, the students move from engineered models into 4 days of Deep Learning.

Bootcamp 5 day structure

The Bootcamp consists of the following folders and files:

  • day 01: Practical machine learning with Python and sk-learn pipelines

  • day 02 PyTORCH and PyCUDA: Neural networks using the GPU, PyCUDA, PyTorch and Matlab

  • day 03: Applied Deep Learning in Python

  • day 04: Convolutional Neural Networks using Keras

  • day 05: Applied Deep Reinforcement Learning in Python

  • docker: a GPU based docker system for the bootcamp

Click to view the full CURRICULUM :





For a docker based system See

  • Ubuntu Linux 16.04
  • Python 2.7
  • CUDA drivers.Running a CUDA container requires a machine with at least one CUDA-capable GPU and a driver compatible with the CUDA toolkit version you are using.

The HTML slides were created using (You can run this directly from Jupyter):

%%bash jupyter nbconvert \ --to=slides \ --reveal-prefix= \ --output=py05.html \ './05 PyTorch Automatic differentiation.ipynb'



This project has been realised with PyCharm by JetBrains

Relevant info:


Shlomo Kashani/ @QuantScientist and many more.

You can’t perform that action at this time.