AI Nugget
AI Nugget Grades Updated
17/11/12 19:43 Filed in: 480
I’ve done another round of grading for the AI Nugget materials, and I believe that I’ve caught up with the presentations given so far. However, quite a few students have not made their material available yet, although they’ve already given their presentation. If you don’t have a grade for your presentation material, and you’ve already done the presentation, please make sure that your material is available either through your page on the AI/KB/HCI Wiki (http://kurfess.wikia.com/wiki/AI_%26_HCI_Presentation_and_Project_Wiki), or on the PolyLearn forum for the AI Nuggets.
0 Comments
AI Nugget Proposal Grades
05/10/12 15:48 Filed in: 480
I’ve just completed the grading of the AI Nugget proposals; please check PolyLearn for your score. I will still accept late submissions and revisions, but they may be subject to late penalties. My usual late penalty is 10% per business day.
AI Nugget Wiki Editing Hints
08/10/12 15:44 Filed in: 480
There are different editing modes for the Wiki we’re using as AI Nugget repository. If you go to your entry through the list at http://kurfess.wikia.com/wiki/AI_%26_HCI_Presentation_and_Project_Wiki, you’ll see an “Edit with Form” button, and a downward triangle next to it, which takes you to the editing pane, where you can use a tab to toggle between “Source” and “Visual” mode. That triangle also lets you go back to previous versions (“History”), and do things like renaming and deleting entries.
Here are a few observations:
From: http://kurfess.wikia.com/wiki/MediaWiki:Edittools
Below are some commonly used wiki markup codes. Simply click on what you want to use and it will appear in the edit box above.
Insert: – — … ° ≈ ≠ ≤ ≥ ± − × ÷ ← → · § Sign your username: ~~~~
Wiki markup: {{}} | [] [[]] [[Category:]] #REDIRECT [[]]
Here are a few observations:
- “Edit with Forms:” Best if you need to make minor changes, such as your presentation title or date. If you’re editing the “Free Text” box, you can use the typical Wiki shortcuts (see also below).
- “Source:” Wiki editing mode; clicking on the “more / +” button in the editing toolbar brings up an overview of the common Wiki shortcuts; I’ve copied them at the bottom of this note). You may need to use this mode if your entry somehow got messed up.
- “Visual:” Allows the use of a toolbar for formatting functions, instead of the Wiki shortcuts. However, do not delete the green blob at the very beginning! It contains the field values for your entry, and if you delete it, your entry won’t appear in the list of presentations. To fix that, you can use the browser’s back button to o to the formatted version of your entry, and from the triangle next to the “Edit” button select “History”. There you can go back to a prior version, and recover the lost field entries.
Common Wiki Shortcuts
From: http://kurfess.wikia.com/wiki/MediaWiki:Edittools
Below are some commonly used wiki markup codes. Simply click on what you want to use and it will appear in the edit box above.
Insert: – — … ° ≈ ≠ ≤ ≥ ± − × ÷ ← → · § Sign your username: ~~~~
Wiki markup: {{}} | [] [[]] [[Category:]] #REDIRECT [[]]
AI Nugget Presentation Material
04/10/12 11:14 Filed in: 480
If you have problems uploading or are reluctant to make your content (e.g. presentation slides) available through Semantic Media Wiki at http://kurfess.wikia.com/wiki/AI_%26_HCI_Presentation_and_Project_Wiki, you can also post material on the PolyLearn “AI Nugget Forum” now. It is under “Course Material and Use of PolyLearn.”
Disappearing AI Nugget Entries
08/10/12 15:44 Filed in: 480
If your AI Nugget doesn’t show up in the 480-F12 AI Nugget presentations list, there’s a good chance that you inadvertently deleted the field entries, which are hidden behind a green blob at the very beginning of the entry in the “visual” editing mode.
You can edit your entries by clicking on it in the 480-F12 AI Nugget presentations list. It's best to do any simple editing by clicking on "edit with form", not the triangle next to it, which pops up a few options with "Edit" being one of them. If you select "Edit", you'll be in "visual" mode, and you should see a green puzzle piece shape at the very beginning of the entry. Don't delete that - it includes important fields for your entry. You can see those in "source" mode. If you delete them, your entry won’t be shown in the list of presentations.
A list of all pages on the Wiki is at http://kurfess.wikia.com/wiki/Special:AllPages, and you can also go through http://kurfess.wikia.com/wiki/Special:WikiActivity, which shows the most recent edits.
You can edit your entries by clicking on it in the 480-F12 AI Nugget presentations list. It's best to do any simple editing by clicking on "edit with form", not the triangle next to it, which pops up a few options with "Edit" being one of them. If you select "Edit", you'll be in "visual" mode, and you should see a green puzzle piece shape at the very beginning of the entry. Don't delete that - it includes important fields for your entry. You can see those in "source" mode. If you delete them, your entry won’t be shown in the list of presentations.
A list of all pages on the Wiki is at http://kurfess.wikia.com/wiki/Special:AllPages, and you can also go through http://kurfess.wikia.com/wiki/Special:WikiActivity, which shows the most recent edits.
480 Article Review Opportunity: "Chaotic exploration and learning of locomotion behaviors" Shim Y., Husbands P., in Neural Computation 24(8): 2185-2222,2012
24/09/12 21:18 Filed in: 480
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.
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:
===================================================
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.
Updated Grades on PolyLearn
28/11/12 22:07 Filed in: 480
I’ve updated PolyLearn with the scores for the following items
* Labs L1 through L8
I’ve graded all of them that were submitted via the respective Web forms; still need to do Lab 9 and Lab 10
* Assignments A1 and A2
If you’ve demoed your assignments A1 and A2, you should have a grade. If I’ll have to run them myself, this will have to wait until next week. There may be time on Thursday after the project displays to do more demos.
* AI Nugget presentations
I believe I’ve graded all the presentations given so far, but still need to do some of the presentation materials.
* Labs L1 through L8
I’ve graded all of them that were submitted via the respective Web forms; still need to do Lab 9 and Lab 10
* Assignments A1 and A2
If you’ve demoed your assignments A1 and A2, you should have a grade. If I’ll have to run them myself, this will have to wait until next week. There may be time on Thursday after the project displays to do more demos.
* AI Nugget presentations
I believe I’ve graded all the presentations given so far, but still need to do some of the presentation materials.
AI Nuggets Presentations - Web Page Updated
19/09/12 13:50 Filed in: 480
I’ve updated the AI Nugget page with the information below, to make it easier to find the signup form and list of scheduled presentations.
If you have a topic for your AI Nugget presentation, you can sign up for it on the Semantic Media Wiki page at the AI KM KB Wiki. To create an entry for your presentation, go to the 480-F12 Nugget Creation Form. You can also view the presentations scheduled so far at
http://kurfess.wikia.com/wiki/480-F12_Nuggets_Page. At the moment, the page still contains some entries from the 481-W12 quarter. Once I figure out how to use the filter feature of the wiki, they won't be shown …
If you’re looking for topic ideas, try my collection of Web snippets in the AI Nuggets Evernote Notebook. You may also find some ideas in a related notebook, KM Nuggets, with an emphasis on knowledge management.
If you have a topic for your AI Nugget presentation, you can sign up for it on the Semantic Media Wiki page at the AI KM KB Wiki. To create an entry for your presentation, go to the 480-F12 Nugget Creation Form. You can also view the presentations scheduled so far at
http://kurfess.wikia.com/wiki/480-F12_Nuggets_Page. At the moment, the page still contains some entries from the 481-W12 quarter. Once I figure out how to use the filter feature of the wiki, they won't be shown …
If you’re looking for topic ideas, try my collection of Web snippets in the AI Nuggets Evernote Notebook. You may also find some ideas in a related notebook, KM Nuggets, with an emphasis on knowledge management.