Advanced Topics in Machine Learning

Topic: Diffusion Models & Applications

Diffusion models comprise a powerful class of generative models.  This course introduces their basic foundations and explores research directions, including applications to science.

The goal in this course is for students to be able to:

• Learn the fundamentals of diffusion models (Lectures

• Gain operational understanding of how to diffusion models. (Colab Notebooks)

• Formulate interesting research challenges.  (Project Proposal)

• Explore aforementioned challenges as a research project. (Final Project)

Those interested in learning more about the architecture of LLMs and other Generative AI models should take EE 148. 

Prerequisites:

• CS 155 (Machine Learning & Data Mining) -- Hard Prerequisite

• EE 148 (Large Language and Vision Models) -- Soft Prerequisite

Instructors and Teaching Assistants

• Yisong Yue (yyue@caltech.edu) -- Instructor

• Hongkai Zheng (hzzheng@caltech.edu) -- Teaching Assistant

• Chris Yeh (cyeh@caltech.edu) -- Teaching Assistant

• Fengze Xie (fxxie@caltech.edu) -- Teaching Assistant

• Austin Wang (akwang@caltech.edu) -- Teaching Assistant

Course Structure

• Weeks 1-4: Introductory Lectures & Colab Assignments

• Weeks 5-9: Guest Lectures (Student Presentations Optional)

• Week 5: Project Proposal

• Week 10: Project Presentation and/or Poster Session

Piazza & Gradescope

We will use Piazza for course announcements.

We will use Gradescope for assignment & final project submissions.

Grading

80% of the grade is on the final project.  20% of the grade is on the Colab assignments

Final Project

The final project should be done in groups (recommended group size is 2-3, max is 4), and one final project document should be submitted per group. The deliverables are: a project proposal due on TBD, and the final project report due at the last day of class (exact date TBD)..