Deep Learning DIY

Unit 1

Module 1 - Introduction & General Overview Module 2a - PyTorch tensors Module 2b - Automatic differentiation

Unit 2

Module 3 - Loss functions for classification Module 4 - Optimization for DL Module 5 - Stacking layers Homework 1 - MLP from scratch

Unit 3

Module 6 - Convolutional neural network Module 7 - Dataloading Module 8a - Embedding layers Module 8b - Collaborative filtering Homework 2 - Class Activation Map and adversarial examples

Unit 4

Module 9 - Autoencoders Module 10 - Generative adversarial networks Homework 3 - VAE for MNIST clustering and generation

Unit 5

Module 11a - Recurrent Neural Networks (theory) Module 11b - RNN in practice Module 11c - Batches with sequences in Pytorch

Unit 6

Homework 3: VAE for MNIST clustering and generation

Homework 3 is in the form of a jupyter notebook. You must complete it and submit it on moodle (for students following the ENS course).

Edit this page on Last modified: April 15, 2021. Website built with Franklin.jl and the Julia programming language.