NEW! DEEP LEARNING DO IT YOURSELF
Please visit the site above. This site is kept for archival purposes only.
Material for Deep Learning hands-on courses: GitHub repositories for code and slides.
Largely inspired by fast.ai course: Practical Deep Learning For Coders (but with a different focus).
The main goal of the courses is to allow students to understand papers, blog posts and codes available online and to adapt them to their projects as soon as possible. In particular, we avoid the use of any high-level neural networks API and focus on the PyTorch library in Python.
Constructive comments welcome!
available courses:
-
Deep Learning: Do It Yourself!
-
Short version taught at école polytechnique (2020)
-
Long version taught at ENS (2019)
-
-
Faster.ai: a 4 days course (part of Master Data Science for Business X - HEC) on deep learning for students with a background in python and ML.
-
Hands-on tour to deep learning with PyTorch with guest lectures by Stéphane d’Ascoli, Andrei Bursuc and Timothée Lacroix
main updates:
-
04/2020 Basics of Deep Learning: Online Course during the lockdown. Spread the knowledge, not the virus !
-
01/2020-03/2020 école polytechnique
-
09/2019-01/2020 ENS course
-
11/26/2019 giving a lecture on deep learning on graphs in the course of Michal Valko Graphs in Machine Learning - MVA
-
11/12/2019 end of the XHEC course with the presentation of projects of the students.
-
07/08/2019 giving a 5h deep learning course for the students of Lipari School on Network and Computer Sciences
-
06/24/2019 starting a summer school Hands-on tour to deep learning with PyTorch with guest lectures by Stéphane d’Ascoli, Andrei Bursuc and Timothée Lacroix
-
01/08/2019 starting our course at école polytechnique with Andrei Bursuc
-
10/21/2018 ressources for faster.ai and projects of the students online.
-
09/14/2018 start of the ENS course: Deep Learning: Do-It-Yourself! 2018
-
05/10/2017 first ENS course: Deep Learning: Do-It-Yourself! 2017
Contributors
with: Alexandre Défossez, Timothée Lacroix, Pierre Stock, Alexandre Sablayrolles, Nicolas Prost, Stéphane d’Ascoli
| GAN | InfoGAN |
 |
 |
Acknowledgement
We gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan V GPU and Google with a Google Cloud Platform Education Grant.