CPSC 625-600 Read-Only Bulletin Board

Last modified: 8/31/10, 12:20PM (Tue)

This page will have all relevant email transactions with the students regarding the AI course, so that everyone has equal information regarding the course material.

Newest transactions will be posted on the top. Regularly view this page to see what's going on between other students and the instructor.

All sensitive material such as your name, email address, etc. will be removed, and also any part of code that is not relevant to the discussion will not be uploaded here.

Article List

Date: 11/30 Title: Presentation schedule
Date: 10/28 Title: Term project info
Date: 9/14 Title: Program #1 correction


Date: 11/30 Title: Presentation schedule

Term project presentation schedule

12/2 75 minutes - 9 minutes each (including Q/A)

12/7 75+20 minutes - 9 minutes each (including Q/A)
	We will meet 10 minutes early: 2:10pm 


Grading of the presentation will be based on the following:

        1. Intro: Did you properly motivate your research problem?
        2. Method:
                Does the proposed method include novel algorithmic
                and/or experimental design?
        3. Results:
                Do the results support the main claims?
        4. Discussion & Conclusion
                Were proper discussion and conclusions given?

Date: 10/28 Title: Term project info


  1. Backpropagation: backprop-1.6.tar.gz (C++ code -- unix)
  2. Neuroevolution: ga.m (Octave code)
  3. SIDA: sida-nat.tar.gz (Octave code)
  4. FOL resolution theorem prover skeleton code: dupeclause.l, fol-dupe-check.lsp, gen-next.lsp, sunify.lsp, theorems.lsp (Lisp)
  5. JAVA version of NEAT called ANJI (with some modifications by YC): anji_2_01-choe.10Oct28.tar.gz. Original source at http://anji.sourceforge.net/.

Final miniproject details

1. Pick a code-base - YC's backpropagation code (in c++) - YC's neuroevolution code (in octave) - YC's SIDA code for sensorimotor semantics (in octave) - YC's FOL resolution theorem prover skeleton code (in lisp) - Your own code - A third-party open source 2. Formulate your research problem - Pick a task - Locate data set (if needed) - Design extensions and experiments 3. Proposal - Team members: max 2 per team. - What is the research problem? - Why is it important/interesting? - What are other people's approaches? - What are the limitations of those approaches? - What is your approach? - What experiments will you do? - What are the expected results? - Who will work on which portion of the project? - Submit by 11/5. * Some project ideas: 1. experiment with SIDA and run on images with various curvatures and with randomly oriented lines. 2. use ANJI for navigation, obstacle avoidance, and other dynamic environmental interactions. 3. KB + question answering system using resolution theorem prover. 4. Dr. Ronnie Ward will give a guest lecture on 11/4 and suggest potential topics as well. 4. Presentation - 10 minutes (8 minute presentation + 2 minute Q/A). - Present final or interim results 5. Final report - 4-5 pages, single space report. - Due by 12/7, 6pm, HRBB 322B.
Date: 9/14 Title: Program #1 correction
I mentioned this in class, but just to make it formal, I'll repeat it.

As for division by zero,

        1. you are not required to check it in (deriv ...)

        2. you are required to check it in (deriv-eval ...)

This means, you cannot use the simple trick I mentioned in class
on how to evaluate expressions in Lisp, involving (eval ...), and
as a result, you have to write a recursive expression evaluator.

$Id: board.php,v 1.5 2004/08/30 23:54:24 choe Exp $