[extropy-chat] Inductive logic system learns games by observing humans

[Neil Halelamien]

New Scientist article description:

http://www.newscientist.com/article.ns?id=dn6914

"A computer that learns to play a 'scissors, paper, stone' by
observing and mimicking human players could lead to machines that
automatically learn how to spot an intruder or perform vital
maintenance work, say UK researchers.

"CogVis, developed by scientists at the University of Leeds in
Yorkshire, UK, teaches itself how to play the children's game by
searching for patterns in video and audio of human players and then
building its own "hypotheses" about the game's rules.

"In contrast to older artificial intelligence (AI) programs that mimic
human behaviour using hard-coded rules, CogVis takes a more human
approach, learning through observation and mimicry, the researchers
say."

Project link (with videos): 

http://www.comp.leeds.ac.uk/vision/cogvis/
http://www.comp.leeds.ac.uk/vision/cogvis/games.html

"In this piece of work we are attempting to learn descriptions of
objects and events in an entirely autonomous way. Our aim is zero
human interference in the learning process, and only to use non scene
specific prior information. The resulting models (object and protocol)
are used to drive a synthetic agent that can interact in the real
world."

Slashdot article:
http://science.slashdot.org/article.pl?sid=05/01/25/0225218&tid=126&tid=14&tid=10

More info on inductive logic programming:

http://www.doc.ic.ac.uk/~shm/ilp.html
http://www-ai.ijs.si/SasoDzeroski/ILPBook/
http://en.wikipedia.org/wiki/Inductive_logic_programming

Research article links:
http://www.springerlink.com/app/home/contribution.asp?wasp=c28459nqtq1jyn5dlftx&referrer=parent&backto=issue,14,23;journal,639,1867;linkingpublicationresults,1:105633,1
http://scholar.google.com/url?sa=U&q=http://www.scs.leeds.ac.uk/afro/galataECAI02.pdf
http://citeseer.ist.psu.edu/muggleton92inductive.html