Academics

Deep Generative Models

Time:Tues./Thur., 13:30-15:05,Oct.11-Dec.30,2022

Venue:W11 Ning Zhai W11;Zoom ID: 330 595 3750

Speaker:Xie Pengtao

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, variational inference, and Markov chain Monte Carlo sampling; 3) parameter learning and structure learning methods, including maximum likelihood estimation, expectation–maximization algorithm, and graphical LASSO; 4) deep generative models (DGMs), including variational auto-encoder, generative adversarial networks, normalizing flows, and  evaluation of DGMs; 5) applications of DGMs in  image generation, text generation, and graph generation.


Prerequisite:

Machine Learning, Probability and Statistics


Reference:

https://pengtaoxie.github.io/dgm.html


DATEAugust 29, 2022
SHARE
Related News
    • 0

      Theoretical Foundations of Neuroaesthetics Applied to Scientific Representations via Generative AI Models and XR technologies

      IntroductionThis two-semester course is structured with the initial semester dedicated to theoretical foundations, followed by the second semester emphasizing practical applications. In the first semester, the focus lies in the exploration of the emerging field of neuroaesthetics and its pertinence to enhancing scientific presentations. Participants will develop competencies in optimizing prese...

    • 1

      Exactly Solved Models in Statistical Mechanics

      IntroductionThe course intends to provide an introduction to the theory of integrable lattice models. Basic examples are the two-dimensional Ising model in a zero magnetic field, the six-vertex model, as well as related two-dimensional models and spin chains.It is planned to explain with simple model examples the concept of matrix transfer, duality between high and low temperatures, the concept...