Spring 2026

Final Project

Proposal, in-class presentation, and final paper — the capstone of the course.

The final project is the capstone of the course and its largest single grade component (50% of the course grade). It is your chance to explore a question about human and machine learning that you find interesting, in the spirit of the class.

Deliverable Weight Due
Proposal (~1 page) 5% Sun Jun 28, 2026, 8:00 PM
In-class presentation (~10 min) 7.5% Fri Jul 17, 2026 — in class, Week 12 (final session)
Final paper (~6 pages) 37.5% Fri Jul 24, 2026, 8:00 PM

Submit written deliverables to the instructor (by DM or email). Dates may shift; any change will be announced in class and here.

Choosing a project

Different people bring different backgrounds and interests — draw on the strengths of yours. Your project does not have to use a specific topic or technique from class. Any project that genuinely pursues human and machine learning is fine, and you should pick something that captures your interest.

Building on an existing research project is okay — for example, applying a model from class to your own thesis data — as long as it is appropriate and your final paper is not identical to something you have submitted elsewhere (see the self-plagiarism note in the syllabus).

Please meet with Joe before the proposal is due to discuss your idea. Email to set up a time. A five-minute conversation now saves you from spending weeks on a question that turns out to be too big, too small, or already answered.

Three (non-exclusive) categories

  1. Experiment. Conduct a small experiment that tests a computational account of human cognition (often one from the readings). As a guideline, a small experiment is ~10–20 people spending about 10 minutes each on a survey or a simple computer task.
  2. Modeling / ML. Take some human behavior — experimental results from a paper we discussed, results from a paper you found elsewhere, or "big data" scraped from the Internet — and explain it by implementing a formal model. You can build your own model or apply one from machine learning. GenJAX is a natural fit here, but not required.
  3. Math / theory. Apply the mathematical ideas we discussed to a particular example, or work out some consequence of a model we covered in class.

Mixed projects that span categories are welcome.

Proposal (due Sun Jun 28, 2026, 8:00 PM)

Your proposal should be about one page, single-spaced, with four sections:

  • Background. Identify the topic your project will explore and give some context. Briefly describe what previous research has found in this area.
  • Question. State the specific question your final project will examine. This should be just one or two sentences — a single clear question, not a vague topic.
  • Method. Briefly describe how you will try to answer the question: details of your experimental procedure, your modeling or analysis approach, and/or your plan for analyzing the model.
  • References. Give at least three references cited in your background.

The proposal is graded pass / fail. The bar is simply that the project is set up clearly enough for Joe to give you useful feedback.

In-class presentation (Fri Jul 17, 2026 — final session)

Presentations take place in the last class. The goal is for everyone to see what their classmates have been working on this semester. Your presentation should be at most ten minutes long. Submit your slides to the instructor immediately before or after class.

Aim to communicate four things:

  • Background — enough context for the class to understand your question.
  • Question — the question your project examines.
  • Method — the method you used (or are using) to answer it.
  • Results — whatever (possibly preliminary) results you have so far, including any implications and limitations.

See the presentation guidelines for tips on giving an effective talk.

Final paper (due Fri Jul 24, 2026, 8:00 PM)

Your paper should be about six pages, single-spaced. There are no strict formatting rules, but here is a structure that works well:

  1. Motivate your research question and succinctly state it, then outline the structure of the paper.
  2. Provide the background — context for your question and any previous work on it.
  3. Describe your methods and results.
  4. Interpret and discuss the results.
  5. Briefly conclude.

Cite sources in an APA-like style if you can, though any clear and consistent format is fine. The most important factor in your grade is motivating and presenting your results clearly.

Provisional and subject to change; updates will be announced in class and on this page.