Home

Licence : Creative Commons Attribution 4.0 International (CC BY-NC-SA 4.0)
Copyright : Jeremy Fix, CentraleSupelec
Last revision : January 23, 2024 09:11
Link to source : index.md
Lectures project page: https://github.com/jeremyfix/deeplearning-lectures/

Forewords These pages are written in markdown format and generated with the pandoc. The stylesheet has been generated from w3schools and the codes are highlighted thanks to pygment. The transformation from pandoc markdown to html is done with a Makefile and is using these template files.

Installation

Below are some elements on how to install the required libraries to work on your own machine.

For the pytorch tutorials, you need pytorch, tensorboardX, matplotlib, tensorflow

For the keras tutorial, you need tensorflow, keras and matplotlib

CPU-Only, Ubuntu 18.04

On ubuntu 18.04, for the pytorch tutorials, it is as simple as :

mymachine:~:mylogin$ python3 -m pip install --user -U matplotplib tensorflow torch==1.3.1+cpu torchvision==0.4.2+cpu -f https://download.pytorch.org/whl/torch_stable.html

On ubuntu 18.04, for the Keras tutorial, it is as simple as :

mymachine:~:mylogin$ python3 -m pip install --user -U tensorflow-cpu matplotplib

Additional ressources

Practicals/Lectures

• Oxford’s CNN practicals
• Nando de Freitas lectures and practicals
• Stanford A. Karpathy practicals
• Master Data Science Paris Saclay
• Fast.ai, J. Howard

Blog posts

• An overview of gradient descent algorithms
• Revisiting sequence to sequence learning, with focus on implementation details
• The unreasonnable effectivness of recurrent neural networks
• Theories of Deep learning