Description: This course introduces how to develop deep generative models (DGMs) by integrating probabilistic graphical models and deep learning to generate realistic data including images, texts, graphs, etc. Course contents include 1) basics of probabilistic graphical models, including Bayesian network and Markov random field; 2) posterior inference methods, including message passing, variat...
PrerequisiteElementary multivariate calculus, elementary statistics. Some basic General Relativity and Statistical Mechanics may help in following the applications.AbstractThe course is targeted to those who know beginning graduate level physics but do not know machine learning. We will cover important methods in machine learning with a view to their applications to current physics such as stri...