Computational Models of Human Behavior
CS88/188 -- Fall 2008 -- TuTh 10:00am-11:50am
Instructor: Tanzeem Choudhury
AboutSyllabusAssignmentsProjectGradingReferences

Final Project

I will provide a few project ideas but you are  encouraged to choose a topic (with my approval) that matches your research interests. Students are encouraged to do projects in groups of two but individual projects are also acceptable. Group projects need to have roughly twice the contribution of an individual project. Feel free to use the available datasets (with proper reference) for your project -
http://www.cs.dartmouth.edu/~tanzeem/teaching/CS188-Fall08/dataset.html

You can choose one of two different flavors of projects -

A project where you implement some of the main ideas from a paper you read in class but explore a new application scenario or create a new and compelling demo.

OR

A project where you propose a new algorithm (or an extension to an exisiting algorithm) that is related to one of the techniques covered in class. You will be graded on the novelty and depth of your idea as well as the implementation. For this type of project you won't be penalized if your idea does not give you the result you expect. But you should make a convincing argument for why you think your idea will be successful in your proposal and devoted enough time exploring why the idea did not work.

The fine print ...

Those of you who are first year graduate students and are unsure about the scope of the project - please come talk to me. It may seem like a daunting task at first but projects can be fun and a great way to get started on research. I will provide some project ideas after October 2, 2008. But first I wanted to give you the opportunity to think about the types of problem that excite you before biasing your thinking. Depending on your interest and experience I am happy to work with you in finding a project that will be a good fit - not all projects have to have a lot of coding. You can explore ideas on how computational systems can be used by people - if you want to propose interesting user study or behavioral experiment towards that goal I am happy to work with you in figuring out the right project. If you are mathematically inclined and want to develop a new algorithm you are welcome to do so but you need to have some way to evaluate your techniques with real data (this can simply be coding it up in Matlab and running some experiments).