CS 598: Principles of Generative AI

Spring 2024

Course Description

Recent advancements in generative AI have equipped machine learning algorithms with the ability to learn from and accurately replicate observed data, creating new, similar data instances. This course provides an in-depth exploration of the key algorithmic developments in generative models, together with their underlying mathematical principles. We will cover a range of topics such as normalizing flows, variational autoencoders, Langevin algorithms, generative adversarial networks, diffusion models, and sequence generation models, etc.

Basic Information

Class time: Tue, Thu 2:00pm-3:15pm
Instructor: Tong Zhang
For students: Course canvas contains detailed information
Also see: Deep Generative Model (CS 598: Spring 2023)

Lectures

Lecture	Topic
1	Introduction
2	Basic Neural Network Models and Optimization
3	Energy-Based Model
4	Variational Inference
5	Encoder Decoder and Auto-Encoder
6	Variational Auto Encoder
7	Normalizing Flow Basics
8	Variational Normalizing Flow and Sampling Basics
9	Markov Chain Monte Carlo
10	Langevin Algorithms and SDE
11	Hamiltonian Monte Cardo and Under-damped Langevin Algorithm
12	Distance, Generation and Convergence
13	Score Matching
14	Diffusion Model (basics)
15	Diffusion model (reverse process)
16	Diffusion model (flow based generation)
17	Diffusion model (practice)
18	GAN (basics)
19	GAN (practice)
20	Neural ODE
21	Disentanglement and representation learning
22	Basic sequence models
23	Transformer
24	Sequence based image generation