---

Course Description

This course will explore the basics of deep generative modeling. It will cover common model paradigms including variational autoencoders, generative adversarial networks, normalizing flow models, diffusion models, and autoregressive models. Students will learn the relative advantages and disadvantages of different model choices, as well as the fundamental design choices that went into each idea. Students will get a chance to explore and present cutting-edge research, and will also implement and experiment with generative models through a course project.

Prerequisite: Knowledge about basic machine learning from 18-661 or equivalent. Proficiency in at least one programming language - preferably Python.

Time & Location

Mondays and Wednesdays, 2:00-3:20 pm ET in SH-236

Links

• Piazza for discussions
• Canvas and Gradescope for homework submission

Instructors

Teaching Assistants