Hands-on tour to deep learning with PyTorch

• Day 1:
  1. (slides) introductory slides
  2. (code) a first example on Colab: dogs and cats with VGG
  3. (code) making a regression with autograd: intro to pytorch
• Day 2:
  1. (slides) refresher: linear/logistic regressions, classification and PyTorch module.
  2. (code) understanding convolutions and your first neural network for a digit recognizer.
  3. (slides) embeddings and dataloader
  4. (code) Collaborative filtering: matrix factorization and recommender system
  5. (slides) Variational Autoencoder by Stéphane
  6. (code) AE and VAE
• Day 3:
  1. (slides) Towards deep learning for the real world by Andrei
  2. (code) softmax temperature; Mixture Density Networks; Bayes by backpropagation
  3. (slides) Generative Adversarial Networks
  4. (code) Conditional and Info GANs
• Day 4:
  1. Reccurrent Neural Networks: slides and associated code
  2. (code) PyTorch tutorial on char-RNN
  3. (code) Word2vec
  4. (code) Playing with word embedding
  5. Structured Self-attentive Sentence Embedding paper code to obtain Glove NLP mini-project
• Day 5:
  1. (slides) Opening the black box
  2. (code) CAM
  3. (code) Adversarial examples
  4. Graph Neural Networks by Timothée

Back to dataflowr