CS 289A: Machine Learning (Spring 2023)


20% of final grade. The project should be done in teams of 2–3 students. Please find a partner.

Please discuss your ideas with one of the Project Teaching Assistants before submitting your initial proposal. Sign up your group for a twenty-minute meeting slot with one of them on this Google spreadsheet. Dates are available from April 4 to April 10. You don't need to have formed your team yet at the time of your appointment. The Project TAs, and their areas of expertise, are:

Bill Peebles, peebles@berkeley.edu: deep learning and large-scale generative models for synthesizing and manipulating visual content.
Eve Fleisig, efleisig@berkeley.edu: natural language processing and ethical AI.
Chawin Sitawarin, chawins@berkeley.edu: security and safety aspects of machine learning, especially robustness against adversarial examples (in neural networks and nearest neighbor methods).



The project theme may be anything related to machine learning techniques discussed in class, including

You are encouraged to design a project that is related to your research outside this course; we really hope that the project will help you make progress in your primary research duties. However, please be honorable and don't suggest a project that you've already fully completed as part of your research.

Initial proposal

The initial proposal is primarily a proposal, and need not be long. Write a few paragraphs describing what you have decided to do. You may have any number of figures and references.


Final report

Grading criteria

The video and the final report will be graded with 5 criteria.

Project ideas

The ideas in this list fall mainly under the fourth category, practical research. If you prefer to revisit an important paper, simply pick a paper. If you prefer to conduct a literature review, simply pick a machine learning topic that interests you. If you prefer to conduct theoretical research, you'd better already know what you're doing.

Other useful data sources: