CPSC 502 -- Artificial Intelligence I
Course Project
David Poole
October 2006
A major component of CPSC 502 will be presentations by students of
current research. The last 5 lectures of the class will be presented
by students. You will also produce written surveys that
will be distributed to the class.
In particular, you should:
- Form a group of any size (including one).
- Choose at least n+1 research papers which refer to each other. (Where
n is the number of people in your group).
- Give me a (1 page) project proposal as soon as possible, but at
least by October 23 stating the members of
your group, the general area of your project and what papers you
chose. Hopefully randomness will ensure there is a diversity of
topics, but you may be asked to coordinate with other groups if your
proposals are very close.
- Give a presentation during one of the last 5 lectures. This
presentation should cover:
- What background information is needed to understand the
papers you chose.
- What contribution each paper made. In particular, you need to
explain the incremental contribution of each paper. Explain what the
result in each paper was and what evidence they used for their
result (e.g., some theorems, empirical evidence that their algorithm was
faster, showing some behaviour that wasn't previously possible).
Each group will be given approximately 15 minutes per member + 5
minutes for questions. A group must give one coherent talk, and each
member needs to present.
- Write a survey paper that covers the background information and
explains the contributions of the papers. These survey papers are due on
the last day of class.
- You will review some of the other papers.
- The revised versions will be distributed to the other members of
the class.
You will have to submit a number of copies of your survey paper, and will be expected
to review a number of papers. The exact number of papers and reviews
depends on the number of groups. Reviewing will be done individually. Reviewers will
be confidential (i.e., the reviewers will know the authors, but the
authors will not know who reviewed your paper). I will know who
reviewed what papers, and reviewing will be a component in the final
grade. I will distribute the review form before the papers are due.
One way to get ideas is to start looking through the course readings
on certain topics - don't wait until we get to the middle or
end of the course, for instance, to look at the articles on planning
or decision theory.
Skim through all the course material keeping an
eye open for something that
looks interesting to you. Even if it's just a general topic or
area, it will provide you with pointers to the literature on
related issues (so will I, so make sure you talk with me
early and often).
David Poole