B652: Computer Models of Symbolic Learning
Spring 2011
Homework 1: Short Project Writeup (due 2/21) and brief presentation (2/23)
Due electronically as a pdf file before class on Monday, February 21.
Submission will be via oncourse.
In this assignment, you will write a brief synopsis of your project
topic and plans, to help clarify the goals and plans of your project
and enable me to give useful feedback. You're encouraged to discuss
your plans and ideas with me and with other students (whether or not
they are in your project group, or even in the class!) before you submit your
project plan.
Project groups should include one or two people. Only one writeup
needs to be done per project group, and the writeup may be submitted
by either student in the group (please be sure to include both
names for two-person projects). The writeup should be 250-500 words
(the equivalent of one or two double-spaced pages).
Each group should prepare a very brief (4-minute) informal
presentation on their project idea, to be presented/discussed in class
on 2/23.
The Project
The goal of the project is to give you a chance to do research on a
symbolic machine learning topic of your choice, taking the methods
presented in class as a starting point. For this you'll critically examine
an area, formulate interesting questions, creatively try to overcome
problems, and analyze what you've learned about machine learning from
your work. In past classes, students have sometimes chosen to
continue these projects beyond the class, and have even had their
project work lead to research publications. Try to select a
challenging topic that you care about, and don't be afraid to take
risks!
The Writeup
The extended abstract should begin with a project title, and then
describe your goals and intended methods.
It should make clear what you are investigating/modeling, what AI
methods you intend to use, and the intended I/O behavior of the
system, and the problems you would like the work to address. It
should also mention (1) why the problem is important, (2) what you
expect to be the hardest part, and (3) what you expect to demonstrate
or learn from the project.
Grading criteria for the project
As a reference, here are the grading criteria that will be used at the
end of the semester for the projects themselves. If you're interested
in a project that doesn't fit into all the aspects of this list,
please talk to me in advance.
- Problem (25%)
- Is it interesting and challenging?
- Model (35%)
- Is the theoretical solution interesting?
- Would it scale up?
- Does it make theoretical claims?
(E.g., saying something about needed knowledge for a task, or
the strengths and weaknesses of a given process, or about what
are the hard and easy parts of the problem you're attacking.)
- Paper (20%)
- Writing
- Motivation
- Relation to other work
- Analysis of strengths+weaknesses
- Clarity on program (All major points should be described, but at a
fairly high level)
- Program (20%)
- Implementation of model
Please let me know if you have any questions!