L01 : Motivating Applications, Machine Learning Pipeline (Data, Models, Loss, Optimization), Backpropagation

L02 : Feedforward Networks: Nonlinearities, Convolutional Neural Networks: Convolution, Pooling

L03 : Jumpstarting Convolutional Neural Networks: Visualization, Transfer, Practical Models (VGG, ResNet)

L04 : Text and Embeddings: Introduction to NLP, Word Embeddings, Word2Vec

L05 : Recurrent Neural Networks and Transformers: Sequence to Sequence Learning, RNNs and LSTMs

L06 : Unsupervised Deep Learning: Generative Adversarial Networks, Variational Autoencoders

LP1 : Project Progress Check-in

  • Hand in a project intermediate project report by the deadline in the course logistics. This will be discussed during class hours with individual teams.

L07 : Online Learning: A/B Testing, Multi-armed Bandits, Contextual Bandits

L08 : Reinforcement Learning I: Policies, State-Action Value Functions

L09 : Reinforcement Learning II: Bellman Equations, Q Learning

L10 : Deep Reinforcement Learning: Function Approximation, DQN for Atari Games, MCTS for AlphaGo

L11 : Advanced NLP: Attention, BERT and Transformers

L12 : Research Case Studies in Deep Learning and Reinforcement Learning

LP2 : Project Presentations by Students

  • Live project presentation during class hours. More details are provided in the project instructions document (see logistics).