CS B552 Knowledge-Based Computation |
An excellent project will address interesting questions, try to overcome hard problems, come up with creative approaches for solving them, and examine not only the strengths but also the limitations of the approach. The point of the paper is showing what you learned about the problem and method and ideas for exploiting what you learned. The paper will be in conference format (which may give a head start on a conference submission about your work!).
Each group should prepare a single joint submission. Each submission will include the following parts:
Please review “Project Components/Grading Criteria” while working on your project, and again before submitting, to make sure you've covered everything that's expected. Grading will follow the listed criteria.
Demo/Late-Breaking Results Session
Everyone is encouraged to demonstrate their programs and present late-breaking results in a closing demo session, but this is not required.
Individual writeups should be 4-5 pages in 2-column AAAI conference paper format, and group writeups 5-7 pages, including sample program output within the paper as needed to highlight key points, any graphs, and references. AAAI Word and LaTeX templates and instructions are available on line. If you are unsure of what to include or what to aim for in the writeup, we'd be happy to talk about it!
Grading for the written materials will be based on the following. (I know different projects may have different types of focuses, and am glad to work things out if not all of these apply to your project. If you believe that some of these criteria aren't appropriate to your project, please discuss this with me as soon as possible.)
1) Problem, Model, and Assessment (30%)
a. Is the problem you’re addressing interesting and challenging? The paper should explain why it is, making clear the motivations and why the approach makes its contribution (this is focused on your creative contribution beyond simply implementing a standard method).
b. Is the theoretical solution interesting?
c. Would it scale up? If you believe it would, please explain why. If not, please explain and justify the limitations.
d. Does it make theoretical claims? (E.g., saying something interesting 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.) Is its performance well evaluated?
e. How informative/appropriate is the chosen evaluation method?
2) Paper (35%)
a. Motivation
b. Relation to other work. The portion on related work should go beyond what we have covered in class, to include the most relevant references to your specific project. A sign of a good project is that there won't be a direct match, but be sure to describe the relationship of the closest prior work to different aspects of your system, even if only certain aspects are relevant, as this will help to establish significance. Online sources such as Google Scholar, the AAAI digital library, and ACM digital library may be helpful. Generally you'll want to discuss at least 6-12 of the most relevant works.
c. Analysis of strengths+weaknesses
d. Evaluation, including discussion of the lessons from the evaluation
e. Clarity on program (All major points should be described, but at a fairly high level, as you’ve seen in papers we’ve studied in class)
f. Presentation
3) Program (35%)
a. Implementation of model and demonstration of its performance. The code should include comments describing major functions/methods etc. If there is a special way to run the program, that should also be mentioned either within the code or in an external README file.
Please take a look at the section on writing AI papers from the MIT AI lab. This has many helpful tips for writing up your research and discusses why to write. (This is an opinionated page which represents only its authors' views.)
Please let me know if you have any questions about expectations, or on anything related to your work. Have fun---this is a chance to let your contributions shine and to be creative. We’re looking forward to seeing what you've accomplished!