The goal of the course project is to apply machine learning to interesting problem domains, thereby gaining in-depth experience with specific algorithms and problem domains. To root your project in reality you are required to find a faculty mentor that will sponsor your project, similar to the 7001 course.

• Projects must be done in teams of two or three students.
• You must form a project team by the end of class on Jan 17
• A single project proposal must be submitted at the beginning of class on Feb 7. Before writing the proposal you should find and meet with the faculty mentor. The project proposal should be 3-5 pages long (see below). Before submitting the proposal you should also meet with me to have the project approved. You are responsible for scheduling that meeting.
• The final project report is due at the beginning of class on April 11. It should be eight to twelve pages long. Your report should at a minimum include the following sections.
• Problem definition. Explain why the problem is interesting and open.
• Prior work (discuss at least 5 related papers)
• Your approach(es). This is the major part of the report
• Results, experimental and/or theoretical.
• Conclusions and ideas for future work.
• References

Guidelines for the Project Proposal

Each team has to submit one project proposal by Feb 7. By this date, each team must have met with the faculty mentor and with me. The team should have familiarized itself with the data and the problem and should also have a clear grasp of what the problem is.

The Project proposal should be 3-5 pages long and clearly address the following

• Problem description. A concise problem description, with a description of the data sets (if applicable). Make sure you communicate why this project is interesting.
• Research goals. A section on what the different outcomes might be. Tell us: when do you judge the project to be successful?
• Project Plan. A project plan, outlining in detail what type experiments will be performed and when (take your best guess). Also describe other means of achieving the project goal, such as consulting specific literature, talking to specific experts.
• Individual Tasks. A description of the tasks that will be performed by the individual team members. Our requirement: Each team member has to engage in interesting machine learning work, so having one student program the software interface while another runs machine learning experiments is not a good division of labor.

Be as concise as possible. Don't stay in the abstract. Be concrete.

Also, several of the items above clearly require input by the faculty mentor. You should therefore be in close contact to your faculty mentor.

Writing a good proposal is a lot of work, since you have to think through the problem, speculate as to what the results might be, and come up with a work plan in advance. However, it's a great exercise for your job once you graduate from Georgia Tech.