CPSC 689-603 Read-Only Bulletin Board

1. Problem statement and significance (30%).

   State the problem that you are trying to address, and explain what significance it has.

2. What you did and why (30%)?

   Breifly explain what kind of computational experiments you did (which software you got, how you modified it), and why you did it (what did you expect to prove, what did you expect as an outcome).

3. What were the results? What is your interpretation (20%)?

   If the result was good, good: Your expectation was justified. If it did not turn out well, that's okay too -- in this case, analyze what went wrong and propose how you will attempt to fix it. If you can plot or visualize the data, please include those in the preliminary report.

4. A brief plan on how you will wrap up the project (20%).

The purpose of the preliminary report is to get you started on the project before it is too late.

In your report for the programming assignment (SIDA option), 
mention these things:

        1. What you have tried (modified)?
        2. Why did you try it?
        3. What did you expect?
        4. What was the result?
        5. What do you think the significance of the result is?
        6. How can you further improve it?

1. For the PCA and the Thal-cor (using xpp) exercises, follow the instructions in the pdf file in each directory.

2. For the SIDA exercise, read the README file and try one (or optionally more-for extra credit) of the 4 "things to try" in section IV.

3. Submission:
   • Submit a hardcopy of your report by the due date, before the class (3/24).

   • Use the turnin command to turn in your source and other results.

     To submit: turnin 689-603 file1 file2 ....
     To check your submission: turnin -c 689-603

4. Grading: (1) The program assignment will count 20% towards your final grade. (2) Extra credit in all cases will be 3% towards your final grade. (3) The remaining 10% (which was initially allocated for three programming assignments) will now be allocated for an intermediate project progress report (details TBA; due by mid April).

Team	Topic
Jinding Dou	Prescott et al. The robot basal ganglia: Action selection by an embedded model of the basal ganglia (see the reading list).
Matt Sanders	Reigl et al., Search for Computational Modules in the C. elegans brain (unpublished draft). Also see Milo et al., Network Motifs: Simple Building Blocks of Complex Networks, Science 298:824--827, 2002.
Iason Leiloglou	Cohen and Beal. Natural semantics for a mobile robot. (see the reading list)
Yutu Liu and Fenghui Zhang	Extension of SIDA. Pierce and Kuipers, or Dennis (sensory-motor learning ; imitation) --tentative
Helga Kocurek, John Kocurek	Palmer, An Evolutionary Justification Of Hebb's Rule (TAMU MS thesis)
Dan Corlette	Ralf Moeller, Perception Through Anticipation: An Approach to Behavior-Based Perception, In Proceedings of New Trends in Cognitive Science, pp184--190, Vienna, Austria, 1997.
Navendu Misra, Rajah Anna Subramaniam Annamala, Ciji Isen	Philipona et al. (from the reading list)--tentative
Jon Whetzel	Whiteson and Stone. Concurrent Layered Learning. In Second International Joint Conference on Autonomous Agents and Multiagent Systems, 2003.
Lingfeng Wang	Tan et al. FPGA-based autonomous robot navigation via intrinsic evolution, Autonomous Robots, 16:5--21, 2004. (PDF available here)
Brad Busse	Rolls. The function of the orbitofrontal cortex. (details TBA)
Yantao Song	James Newman and Bernard J. Baars and Sung-Bae Cho. A Neural Global Workspace Model for Conscious Attention, Neural Networks, 10:1195--1206, 1997.
Noah Smith	Plate, Tony A. "Analogy retrieval and processing with distributed vector representations." "Expert Systems: The International Journal of Knowledge Engineering and Neural Networks." Special Issue on Connectionist Symbol Processing, 17:1, pages 2940, 2000.
Heejin Lim, Jaehee Jung, Seongjin Shin	An experiment of 2-D pole balancing using thalamo-cortical loops
Jim Bethancourt, Blake Stoker, Josh Dahms	Brain-machine interface
John Meeks	ESP in the Predator-Prey domain
Deji Coker	J. Mira, A. E. Delgado, A. Manjares, S. Ros, and J. R. Alvarez. Cooperative Processes at the Symbolic Level in Cerebral Dynamics: Reliability and Fault Tolerance, In R. Moreno-Dian and Jose Mira-Mira (Editors) Brain Processes, Theories, and Models: An International Conference in Honor of W. S. McCulloch 25 Years after His Death, MIT Press, Cambridge, MA, 1996.

1. Is the SIDA agent different from Bayesian observers and/or theorists? If so, explain what the differences are. If you think there is no difference, explain why.
2. For complex objects, what kind of invariance would be necessary, if any such invariance can be found at all.

1. What are the differences between a Bayesian observer and a Bayesian theorist as Jepson and Feldman defines?
2. Is the Bayesian theorist proposed by Jepson and Feldman sufficient enough to become a perceptual agent (i.e., is there anything to add)? Present your case based on a sound argument, whether you think the answer is yes or no.

So, I am giving you a chance to resubmit if you wish, without penalty, by Wednesday in class. If you think you already followed the instructions in the lecture slides and also in the article below, then you do not need to resubmit.

Being lengthy does not guarantee you a good grade, and actually, if you make the same point redundantly here and there, it can hurt your grade, so when revising, please make sure that you make it succinct.

1. Submission guideline:
   • Write a draft, print it out, proofread, and write comments on it.
   • Revised your comments (at least once), and print out the final copy.
   • Submit the following in hardcopy:
     1. The initial draft (x1) with your comments; and

        This will help you to think more clearly. A submission without an edited draft will not be accepted. If you wish, you can use the track changes feature in your word processor.

     2. Two idential copies of the revised, final draft (x2).

        One copy will be returned to the student, and one will be filed by the instructor.

     3. The submission deadline is right before the class on the stated due date.

2. Grading criteria (total 100%):
   • Clarity, including factual correctness and organization (40%)

     Is the comment clearly written with a linear progression of ideas?

   • Originality and deepness of thought (30%)

     Do the comments present original thought by the student and not just a reiteration of the points made in the paper?

   • Soundness of analysis (30%)

     Is the analysis, if any, of the article as presented by the student reasonable given the article's content and its general context?