CS440: Introduction to Artificial Intelligence
Fall 2015
Project

The project gives you an opportunity to explore a topic in AI that is of interest to you. The course covers fundamentals and does not include topics specific to very many subareas of AI. So here's your chance to follow your interests and learn a bit more in depth.

The project should be a combination of hands-on and reading. You could do one of three types:

  1. Existing algorithm/new problem: Apply algorithms used in class or available through the Russell and Norvig code repository to new problems. You might need to modify the algorithms to support the new problems.
  2. Replicate Result: Replicate a result reported in a publication, which could include downloading and using existing code.
  3. New approach/problem: Write your own AI algorithm(s) and apply it to a data set found via the Internet or one that you make up.

In all of these cases, you will be required to read at least 2 papers from the published scientific literature and summarize them in your paper. Publications must be from academic venues. I recommend using Google Scholar to search for such papers. Articles from the popular press or blogs do not count and be careful with papers downloaded for a personal website when there is no reference to a publication listed.

You should work in teams of 2 or more students (up to 4). I will set up a discussion thread for people seeking partners. For the distance students, if the logistics prove too difficult, I may make exceptions, but please try to find someone first. It really helps to bounce ideas off of someone else.

Proposal [8% of project grade]

Submit via Canvas a short description of your proposed project by October 12 at noon Mountain Time. It should include: a title, names of your team members, name of the team coordinator, a description of what you will be doing, and a reference to 1 published paper on the topic. It should also list one of the project types (1-3 above).

Note: every member of the team should be submitting this to ensure that everyone is on-board. Only the submission from the team coordinators will be read; the others will be checked to make sure that they are part of the same team. Refer to your team by the team coordinator's name.

Rubric: required components [70 pts], relevance to AI [15 pts], readable/grammatical [15 pts]

Presentation [28% of grade]

Develop good presentation materials. Practice your talk. Oral presentations and posters should cover: what you did, how it is AI, and what you learned. The "talk" for posters should be a very short summary of the important points which invite the listener to follow up with questions.

For distance students, you will have several choices. You can come to class to present. You can give your talk live via Skype (several students did so when I taught CS540 in the spring). You can create your own video for your talk.

Rubric: Good speaking style [15 pts], Understandable materials (slides or posters) [15 pts], Well Organized [10 pts], Explained focus/objective [20 pts], Described what was learned [20 pts], Quality of the content [15 pts], Feedback to others [5 pts]

Note: Part of your grade will involve giving feedback to another team. You will be provided with forms. You can earn 5 pts extra credit by giving feedback to an additional team.

Written Report [64% of grade]

Submit via Canvas the PDF file of your written report by Sunday December 13 at noon Mountain Time. The written report should clearly describe the focus of your project (what were you trying to achieve), how it related to AI, what each of you did, what papers you read, what the papers said that were relevant to your project, what results you collected and what you learned.

The paper should follow standard guidelines for academic papers and must be formatted in a standard format from AI used for one of the major conferences, AAAI. The formats are available at: http://www.aaai.org/Publications/Author/author.php The paper must be 4-6 pages in length. Underlength papers will receive a lower grade. Portions of the paper that exceed the length limit will not be read or graded. Your reference section (last section in the paper) should list at least 2 references to actual publications (wikipedia entries, random websites and the Russell and Norvig text do not count!), which must also appear in the prose as citations with descriptions. Your paper header should include the names of all team members.

Rubric: Introduction/motivation [20 pts], Clear description of what was done and how it was done [20 pts], Good results and observations/conclusions [20 pts], Organization [10 pts], Spelling/grammar/readability [15 pts], contribution of each team member is clear [15 pts]