Environment setup, jupyter, python and numpy basics
All tutorial materials are available from the course tutorials repo. We recommend cloning this repo and pulling updates from it if you want to run the notebooks yourself.
Additionally, the tutorial notebooks can be viewed in your browser by using nbviewer.
Supervised learning context, binary and multiclass logistic regression
MLP model, activations, backprop, loss functions and optimization in PyTorch
Convolutional and pooling layers, architectures, spatial classification, residual nets.
RNN implementation, sentiment analysis, attention.
Transfer learning definition, contexts, fine-tuning pre-trained models, unsupervised domain adaptation.
The RL setting, openAI Gym, Deep q-learning for Atari games.
Filters on graphs, graph convolution layers, semi-supervised node classification