In this course, we will cover topics which lie at the intersection of Deep Learning and Generative Modeling. We will start with basics of joint distributions and build up to Directed and Undirected Graphical Models. We will then make a connection between Graphical Models and Deep Learning by having an in-depth discussion on Restricted Boltzmann Machines, Markov Chains and Gibbs Sampling for training RBMs. Finally, we will cover more recent Deep Generative models such as Variational Autoencoders, Generative Adversarial Networks and Autoregressive Models.
Module 1 : A brief introduction to Directed Graphical Models Module 2 : A brief introduction to Markov Networks, Using joint distributions for classification and sampling, Latent variables Module 3 : Restricted Boltzmann Machines, Unsupervised Learning, Motivation for Sampling, Markov Chains, Gibbs Sampling for training RBMs, Contrastive Divergence for training RBMs Module 4 : Variational Autoencoders, Autoregressive models, GANs