[an error occurred while processing this directive]

ICS-175A, Project in AI, Winter 2010
grades | home work | lecture notes| projects

  • Classroom: ICS 180
  • Days: Tuesday & Thursday
  • Time: 12:30 - 1:50pm
  • Instructor: Rina Dechter - dechter@ics.uci.edu
    Office: DBH 4232
    Hours: Tuesday 2-3 pm
  • TA: Natalia Flerova, nflerova@uci.edu
    Office: DBH 4099
    Hours: Monday 4-5 pm

Check out some of our best projects:

Final Announcements

Demo presentation

As we discussed in class, the demo presentation is ***not** a slot of 20 minutes meetings. We will meet in two intervals. 9:30-11:00 (group 1) and 11:30-1:30, group 2. The meeting is at 4011 DBH.

Each team will have their station in the room and they will demonstrate during period to student members and to us their system. See the assignment below to groups. Those who did not reserve an interval please *send me an email*.

There are a few teams that contacted me and have an exam during the relevant periods. Only those team that received an explicit approval message can come at 12:30.

During the demo period you will: 1. setup your demo in a desk in a room and when your tern come just show a demo and answer questions. 2. Bring your final reports. The final reports should have the same structure of the midterm reports but can now be longer, up to 10 pages. You should also include a user manual as discussed in an earlier message. There is no need for any power point presentation for the demo. Juts be prepared to show how your system work and answer questions from everybody.

Final report and code

The final report should contain up to 10 pages and follow the same guidelines as the midterm report, with background information, the devision of the work between the teammates etc. In addition to that, it should include summary of all your work and the evaluation of the results.

The final report should contain a section denoted "User's manual", that in details explains how the program should be compiled and run. The level of details should be enough even for a user that has minimal experience with computers to be able to compile and execute the code. The manual should also contain the description of typical program behaviour, explanations of GUI features, if there's a GUI, and input parameters and outputs, if there is no GUI. The latter is of utmost importance - the user must have a full understanding of how to decipher program's output results. If the program requires specific input files, they should be enclosed. We are aware that some projects may have a problem with this requirement. If you do, please get in touch with us and we will address this issue in a case by case basis.

In addition to the final report you are asked to submit both source code and executable file of the final program for evaluation. Please submit them to the EEE dropbox.

The code will be evaluate as a "black box" - that is if it is not compiling and/or not running we will not be able to go further.

Course Goals:
Students are required to do a project in Artificial Intelligence. Weekly progress reports will be graded.

Final project: submit a report + code + demo + presentation.

Students will be required to work independently and be expected to acquire all the knowledge necessary for the project. They will have to fill-up the necessary gaps in their background. TA and instructor will help with an introductory overview and refer the students to the appropriate literature. In particular, basic knowledge in Bayesain networks and Constraint processing will be necessary.

We will have a class meeting each week on Tuesday. we will have individual/group meetings and TA meetings each Thursday.

Final grade: Weekly project reports, 20%.
Demo-presentation: 40%
Final report: 40%.

Projects Ideas:
There will be two types of projects. Project of building an AI system that provide advise and ans solve some problem in some area. We will use graphical model frameworks and focus primarily on Bayesian Networks (BN) and constraint networks. Students can choose projects from other areas in AI, such as search and and planning. The second type is "Research projects". Students will delve into a research question with a graduate student and will conduct empirical investigation pursuing the question at stake.

Students can select one of the proposed projects or may come up with their own idea for an AI project.

    For any assignment that you submit you should always state at the top of the report: the team number, the names of team members and the project title.

    • Progress report 1. Due February 2

      For the first report should be a two page progress report. The first half/full page of background on your project, including references wherever relevant.

      The second page ahould describe your progress.

      In your progress you should explain:

      1. How does the project built upon what is available in the literature, and out there.
      2. what is the architecture of your project (different modules and who is doing what on the team)?
      3. what tools will you use, or have started to use.
      4. Is there any data that you need to access?
      5. How would you evaluate your project. What is the criteria for success.
      6. What initial code you started to develop.

    Resources on the Internet


    Week Topic Date   Information    Assignment
    Week 1
    • Overview of necessary background in Bayes networks. Start forming groups for projects.
    01-04 Lecture 1: Constraint networks overview

    Lecture 2: Bayesian networks overview
    Project ideas
    Week 2
    • Presentation of specific projects. Each group provides a proposal for two possible projects it considers.
    01-11 Lecture 3: Building Bayesian networks

    Advising first year student
    Week 3
    • Progress report.
    01-18 List of teams and project topics Report 1
    Week 4
    • Progress report.
    Week 5
    • Progress report.
    Week 6
    • Progress report.
    02-08 Midterm report Midterm presentation
    Week 7
    • Mid-quarter progress report and presentation
    02-15 Presentation order
    Week 8
    • Mid-quarter progress report and presentation
    Week 9
    • Demo-presentations.
    Week 10
    • Demo-presentations.
    Week 11
    • (Finals): final report + code + demo-presentation.