The focus for the last few weeks of the semester will be to propose and complete a final project of your choosing. You will collaborate in groups of 2 to 4 individuals, preferably within the same lab section (across lab is okay as long as all group members are able to attend one of the labs all together). Note that the recommended group size is 3. Groups of 4 will require prior approval from the instructor, and the instructor reserves the right to modify groups as necessary.

Timeline & Deliverables

The deliverables and when they are due are as follows:

  • Each student must fill out a Google Form indicating their preferred project partners and any project topics they may be interested in. This is due November 13. Based on these preferences, groups will be formed by November 14. The instructor reserves the right to adjust groups as needed for project balance or logistics.

  • A per-group proposal (1 page), including a timeline and full details, is due November 18. You should have a draft to discuss with your instructor for the November 17 lab meeting. (5%)

  • Weekly checkpoint demonstrations in lab (to your lab instructor and/or classmates) on November 24, December 1, and December 8. (5%)

  • A conference-style short paper (~4–6 pages) due December 19th. (70%)

  • A final presentation during the last class period, December 9. (20%)

  • All project related material (e.g., code and data) submitted through Gradescope.

Project Ideas

Your project must be related to the field of machine learning and it should go beyond what we have covered in the course in terms of assignments or core lecture materials. More detailed topics, data/paper resources, and advice is available here.

When formulating your project and proposal (below), think about how you can implement phased development—incremental subgoals that help you make consistent progress even if the final goal turns out to be difficult.

Proposal

5% of your grade

By the proposal deadline, you will submit a full proposal. Your full proposal, which should be submitted to Gradescope, includes:

  • A 1 page description of your project (see below for details on expected content), submitted as a PDF (proposal.pdf)

  • A rough timeline of weekly goals (included in the same PDF)

You should brainstorm ideas before the November 17th lab meeting so that we can help steer your proposal in a productive direction.

Your full proposal will include the following:

  • The title and group member names

  • Central hypothesis: What is the main question you would like to answer (i.e., your goals)?

  • Problem Description: What is the problem the project will seek to address? What would a solution look like? Who would benefit? How will you know if you’ve solved it?

  • Algorithms: What is/are the central algorithm(s) for your project? Do you plan to implement them or to use libraries?

  • Data: What data are you using, and where are you getting it?

  • Experiments: What experiments and analyses do you plan to execute?

  • Impacts: What potential societal impacts or ethical considerations are relevant?

  • References: Papers, data sources, and other relevant materials.

Your proposal must also include a phased development plan, specifying intermediate milestones and weekly goals.

Checkpoints

5% of your grade

Each week, you will provide an update to your instructor on your progress (submitted through Gradescope). Your grade will be determined by your ability to:

  • Make sufficient progress or proactively seek assistance

  • Document updated accomplishments and goals

  • Demonstrate progress (e.g., code review, figures, analysis)

  • Participate in weekly stand-up meetings during lab

  • Complete weekly reflection surveys

Paper

70% of your grade

Your 4–6 page final paper is due through Gradescope by midnight on the paper deadline.

All relevant figures and tex files should be included in your Gradescope submission. You must use the provided LaTeX templates. Details about the paper requirements are available here.

Presentation

20% of your grade

Your group will present during the last class period, December 9. Each group will have 5 minutes to present a brief overview of their work. All members must present.

Follow the posted presentation guidelines and rubric. Suggested outline is available here: Presentation Rubric.

Submitting your Project

All final materials must be submitted through Gradescope. Please upload:

  • A PDF of your final paper (including any files needed for compilation)

  • A PDF of your final presentation slides

  • A ZIP file containing your project code and a README

  • Any data used for evaluation (or contact instructors if large)

The goal is to make it straightforward to replicate your results.