Quiz 1 Re-grade and Results

I re-graded the questions about human vs. artificial intelligence, and gave significantly higher partial credit for those answers that have a healthy degree of truth to them (usually 70-80%). This brought up the average score for these questions in line with the other ones, for a range of 6.86 to 10, and an overall average of 85.34 for all the students who took the quiz.
0 Comments

Lab 1 Deadline Extended to Thu, Sep. 27

Since I announced the first lab in at least one of the two sections last week on Thursday only, I'm extending the deadline until Thursday, end of the day (23:59).
0 Comments

Lab 2 Submission

I’ve just enabled the PolyLearn "Lab 2 Submission" link under Chapter 2 “Intelligent Agents”. Please submit the following files for Lab 2 there:
  • a plain text file (not a MS Word document) named README.txt with your name, a brief explanation of your program, and instructions for running your program
  • the Java source code for your agents
  • the Java executable (class file) for your agents
If you haven't done so, make sure to also submit observations about the behavior of your agents via the Lab 2 Web form.
0 Comments

Lab 2: Auto-Step Solution for BotEnvironment

Here’s a solution for the missing Auto-Step behavior in the environment for Lab2; thanks, Alan!


Author: Alan Phu Truong.

Solution:

Instead of using the following to start your environment in Linux/Mac:
java -classpath .:WumpusEnvironment.jar BotEnvironment.WumpusEnvironment

Use:
java -Xint -classpath .:WumpusEnvironment.jar BotEnvironment.WumpusEnvironment

On Windows, replace the colon with a semicolon:
java -Xint -classpath .;WumpusEnvironment.jar BotEnvironment.WumpusEnvironment

AutoStep seems to work under more circumstances with this flag.

-Xint: Operate in interpreted-only mode. Compilation to native code is disabled, and all bytecodes are executed by the interpreter. The performance benefits offered by the Java HotSpot VMs' adaptive compiler will not be present in this mode.See http://download.oracle.com/javase/1.3/docs/tooldocs/linux/java.html



I’ve also added a pointer to additional material on Blackboard (under BotEnvironment JavaDocs, BotEnvironment Tutorial, and BotEnvironment FAQ) to the Lab 2 description.


If you want to be updated about postings to the Blackboard Discussion forum, click on the forum title, and then on the “Subscribe” button at the top. Subscriptions can be enabled or disabled for a specific forum, so not all of them will have the “Subscribe” button.
0 Comments

TRAC Wiki Login Problems

Apparently the transition of our CSL servers to the use of current ITS credentials (username/password) isn’t quite complete. The system that hosts the wiki still uses last quarter’s credentials from vogon. So if you have problems logging in, try your old password. If you don’t remember it, or it still doesn’t work, you should see one of our sysadmins.
0 Comments

Quiz 1 - Partial Credit

It looks like the transition from Blackboard to PolyLearn caused some problems with multiple choice questions and partial credit by setting the percentage values for partial credit to zero. If you suspect that this is the case, let me know.
0 Comments

480 Article Review Opportunity: "Chaotic exploration and learning of locomotion behaviors" Shim Y., Husbands P., in Neural Computation 24(8): 2185-2222,2012

I have received a request to review an article for the ACM Computing Reviews. It's of moderate interest for me, but if anybody from this class is interested, let me know. This could be the basis for your AI nugget presentation, or use it as extra credit, or for replacing a lab, (partial) assignment or quiz.

F.K.


===================================================================
Review of an already published article for ACM Computing Reviews and ComputingReviews.com (http://www.computingreviews.com)
(This review will be published on the ComputingReviews.com Web site, and is not about acceptance or rejection. It is intended to provide feedback on already published work. )

"Chaotic exploration and learning of locomotion behaviors" Shim Y., Husbands P.
Neural Computation 24(8): 2185-2222,2012

CCS Classification:

Abstract:
We present a general and fully dynamic neural system, which exploits intrinsic chaotic dynamics, for the real-time goal-directed exploration and learning of the possible locomotion patterns of an articulated robot of an arbitrary morphology in an unknown environment. The controller is modeled as a network of neural oscillators that are initially coupled only through physical embodiment, and goal-directed exploration of coordinated motor patterns is achieved by chaotic search using adaptive bifurcation. The phase space of the indirectly coupled neural-body-environment system contains multiple transient or permanent self-organized dynamics, each of which is a candidate for a locomotion behavior. The adaptive bifurcation enables the system orbit to wander through various phase-coordinated states, using its intrinsic chaotic dynamics as a driving force, and stabilizes on to one of the states matching the given goal criteria. In order to improve the sustainability of useful transient patterns, sensory homeostasis has been introduced, which results in an increased diversity of motor outputs, thus achieving multiscale exploration. A rhythmic pattern discovered by this process is memorized and sustained by changing the wiring between initially disconnected oscillators using an adaptive synchronization method. Our results show that the novel neurorobotic system is able to create and learn multiple locomotion behaviors for a wide range of body configurations and physical environments and can readapt in realtime after sustaining damage.
===================================================
Article Review

The article has already been published, and the review is intended for additional feedback; if accepted, the review will appear in the ACM Computing Reviews (deadline is probably around Oct. 18).

My expectations for a review are:
- you read the article (which I will send you); usually I read such articles at least twice
- you will check the Internet for related articles (the ones mentioned in the bibliography section, and possibly others the authors may have omitted); typically I won't read all of those, but I'll look at the abstracts, skim the most relevant ones, and read those that help me understand the one under review
- use your best judgement to evaluate the quality of the article, based on a review form provided by the journal editors
- write a review for people interested in the topic; this one is usually short (about 250 words)

Overall, such a review typically takes me 5-10 hours; count on spending maybe a little more if you're not familiar with the topic. In both cases, I will act as the main reviewer, and reserve the right to use or omit your contributions. I will acknowledge your assistance to the editors. If I use any of your contributions for the ACM Computing Reviews, your name will also be forwarded as a co-author of the review.  In that case, you need to sign a copyright release form.
0 Comments

Joining Teams on PolyLearn

It looks like the method of using “enrollment keys” doesn’t work in PolyLearn; maybe it needs to be set up before students can join the class. The only pointer I could find in the documentation is
Enrolment keys will cause the user to be automatically added to the group when they enroll in the course using the key.”
I wasn’t able to find instructions for students to join groups, however. I guess then I’ll just have to manually populate the groups. To make this easier for me, please put your team member information on the team TRAC Wiki.

I’ve removed the enrollment keys, and added a leading zero to Teams 1-9 to list them in their intuitive order, rather than Team 1, Team 10, Team 11, …, Team 2, Team 3, ...
0 Comments

480 Teams on PolyLearn

Using the “groups” feature in PolyLearn, I’ve created entries for 16 teams. Most likely we’ll use them just for grading purposes, but maybe there are other uses for this as well.
To join the group for your team, please use the enrollment key “Team X”, consisting of the word “Team” followed by a space character and your team number without leading zero. So for Team 1, this is “Team 1”.
0 Comments

480 Section 03 Merged into Section 01 on PolyLearn

If you’re in Section 03 of 480, you should now see an entry for 480-01 in your PolyLearn course list. I’ve asked the PolyLearn admins to merge the two sections.
0 Comments

Quiz 1 Availability and Visibility

Quiz 1 will be available all day on Tue, Sep. 25. In contrast to Blackboard, where quizzes became visible to students only when they can actually take the quiz, PolyLearn seems to show a link on the course overview with more details after the link (e.g., “The quiz will not be available until Tuesday, September 25, 2012, 12:00 AM”). Students who added the class later may not be on the access list for this class in PolyLearn; I believe that this is done overnight, leading to a one-day delay in most cases.
0 Comments