This page refers to the Spring 2017 offering of CSE 674 only. The information on this page does not necessarily apply to every offering of CSE 674.
Artificial Intelligence/Machine Learning
This course is focused on probabilistic graphical models (PGMs). We will study both directed graphical models (Bayesian networks) and undirected graphical models (Markov Networks, also known as Markov Random Fields). Topics will include methods of representation, independence properties, exact inference algorithms (variable elimination and belief propagation), approximate inference algorithms (variational and Monte Carlo), learning PGMs (parameters and structure) and causality. Relationship of generative and discriminative PGM methods to deep learning is also explored.
CSE 4/574 or equivalent
M.S.: This course fulfills one Artificial Intelligence Core Area (Depth) requirement.