Numbers
Due: February 8, 2008 23:59:59 EST
Please have one of your
group members submit this assignment
via tsquare. Please include the names of everyone in your group
in the body of the email message. You may send text or pdf.
The assignment is worth 5% of your final grade (or 20% of your project grade). More importantly, if you don't do it you will have violated a requirement of the project and will suffer greatly for it.
Why?
By the due date, you should have familiarized yourself with the data you're going to use and the problem you're going to pursue. In other words, you should have a clear grasp of what the problem is. You should have found a faculty mentor, or run the idea past someone with some experience with your domain.
What to turn in
A three-to-five page formal description of your proposed project. It must clearly address:
Problem description. A concise problem description, including a description of the data sets you will use (if applicable). Make sure you communicate why this project is interesting.
Research goals. A discussion of what the different outcomes might be. In particular, tell us how you will know when the project is successful.
Project Plan. A project plan, outlining in detail what type of experiments will be performed and when (you won't be sure at this point but make your best educated guess). Also describe the means you will use to achieve the project goal, such as consulting specific literature, talking to specific experts, and so on.
Individual Tasks. A description of the tasks that will be performed by the individual team members. Be careful about this. Each of you is in a class about machine learning, thus each team member has to engage in interesting machine learning work. In other words, having one student program the software interface while another runs machine learning experiments is not a good division of labor.
Be concise, but do not achieve conciseness by staying in the abstract. Be concrete.
As has been pointed out before, writing a good proposal is a lot of work, because you have to think through the problem, speculate about what the results might be, and come up with a work plan in advance. I know because I have to do this sort of thing all the time. You may think of this as my simply sharing the pain, or of my providing a great exercise for your career beyond Georgia Tech. Whatever gets you through the night. Regardless, this is a good thing.