CS 7641
Machine Learning
Group Project Overview

Why?

The goal of the course project is for you to gain in-depth experience with specific machine learning techniques and algorithms by applying them to some interesting problem domains. In addition you should also gain an appreciation for what it means to have a result in the field.

What?

Projects must be done in teams of two or three students. If you wish you should feel free to ground your project in some sense of reality by finding a faculty mentor who will act as an unofficial advisor for your project. Think of your advisor as an informal version of what you might have had for 7001. Again, this is not required, but I would highly recommend it.

There are a few milestones (dates are available from the schedule page):

  1. You must form a team, and very quickly.

  2. You must submit a short, informal proposal soon after. I must approve your idea.

  3. You must submit a longer proposal.

  4. You must submit a progress report. It should look a lot like a preview of your final paper and incorporate any changes that we agreed upon.

  5. You must submit a paper. Consider this your submission to the conference. It will be reviewed by others.

  6. You must submit the final package, including minor changes to the paper as suggested by the reviewers.

The final package is due just before the last week of class (dead week, I believe the kids call it). It consists of:

  1. A NIPS-style conference paper (see the resources link to find out what that entails) written by your group.

  2. A short presentation. The order of presentation will be more-or-less random.