phyllis@utcsrgv.UUCP (Phyllis Eve Bregman) (01/16/84)
UofT Department of Computer Science Seminar Schedule for
the week of January 16, 1984
Tuesday, January 17th, 3:00 P.M., GB244: Professor Larry Rendell
Department of Computer Science, University of Guelph, Guelph,
Ontario: "Efficient generalization learning in search".
ABSTRACT: Generalization learning is inductive inference,
acquisition of conceptual knowledge. It can be accomplished
efficiently by structuring statistics obtained from observation
of a given primary task. Such an approach has wide application
in noisy environments.
The probabilistic learning system (PLS) is currently being
studied using the domain of search in state-space problems
and games. Feature space clustering, knowledge accumulation,
and regression have resulted in economical discovery of locally
optimal evaluation functions. Adding an upper layer of
(parallel) learning increases stability and power; adding lower
layers may allow feature formation from elementary data
(i.e. full inductive capability).
Some unifying concepts and methods are suggested for efficient
generalization learning.
--
Phyllis Eve Bregman
CSRG, Univ. of Toronto
{decvax,linus,ihnp4,uw-beaver,allegra,utzoo}!utcsrgv!phyllis