Hi Shane,
I and Ben met Nick Cassimatis (the author of Polyscheme, student of Marvin Minsky) at DC last month in FSS-04, where each of us gave a presentation (see http://xenia.media.mit.edu/~nlc/conferences/FSS04Schedule.pdf).
Polyscheme is in the "cognitive architecture" family (with Soar, ACT, and so on), though he has some new ideas. Since I haven't found any detailed technical paper on the project (Cassimatis' talk at FSS-04 was not accompanied by a paper, and his PhD thesis isn't on-line), I cannot make confident comments on it, except that the project seems to be still in an early stage.
For instance, reasoning plays a central role in the system, but I haven't known what is new there. The basic operations include "forward inference, subgoaling, grounding, representing alternate worlds, and identity matching", which sounds strange to me --- they don't form a reasonable partition of reasoning.
I'm sure Ben has more to say about Polyscheme vs. Novamente, since he talked with Cassimatis during the conference.
Pei
----- Original Message ----- From: "Shane" <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Wednesday, November 24, 2004 8:26 AM
Subject: [agi] Polyscheme
Have any of you heard of Polyscheme before?
There's an overview here:
http://www.cassimatis.com/polyscheme.html
It sounds a lot like Novamente.
Shane
Find local movie times and trailers on Yahoo! Movies. http://au.movies.yahoo.com
-------
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
-------
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
