Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utgpu!water!watnot!watmath!clyde!rutgers!ames!ucbcad!ucbvax!RED.RUTGERS.EDU!KAPLAN
From: KAPLAN@RED.RUTGERS.EDU.UUCP
Newsgroups: mod.ai
Subject: Seminar - Decomposition for Hierarchical Problem Solving (Rutgers)
Message-ID: <12290791900.46.KAPLAN@RED.RUTGERS.EDU>
Date: Tue, 31-Mar-87 10:36:22 EST
Article-I.D.: RED.12290791900.46.KAPLAN
Posted: Tue Mar 31 10:36:22 1987
Date-Received: Sat, 4-Apr-87 10:34:46 EST
Sender: daemon@ucbvax.BERKELEY.EDU
Distribution: world
Organization: The ARPA Internet
Lines: 34
Approved: ailist@sri-stripe.arpa


	PhD Oral Qualifying Examination for Mr. S. Mahadevan

Mr. Mahadevan's examination is scheduled for Wednesday, April 1 at 10:30 AM
in Hill 423. The examination committee is chaired by T. Mitchell, and includes
T. McCarty, J. Mostow, and L. Steinberg. DCS faculty are welcome to attend;
graduate students are invited to the public portion of the examination. Mr.
Mahadevan's dissertation proposal is abstracted below:

	LEARNING DECOMPOSITION METHODS TO IMPROVE HIERARCHICAL 
		PROBLEM-SOLVING PERFORMANCE

Previous work in machine learning on improving problem-solving
performance has usually assumed a state-space or "flat"
problem-solving model.  However, problem-solvers in complex domains,
such as design, usually employ a hierarchical or problem-reduction
strategy to avoid the combinatorial explosion of possible operator
sequences. Consequently, in order to apply machine learning to
complex domains, hierarchical problem-solvers that automatically
improve their performance need to designed.  One general approach is
to design an interactive problem-solver -- a learning
apprentice -- that learns from the problem-solving activity of expert
users. In this talk we propose a technique, VBL, by which such a
system can learn new problem-reduction operators, or decomposition
methods, based on a verification of the correctness of example
decompositions. We also discuss two important limitations of the VBL
technique -- intractability of verification and specificity of
generalization -- and propose solutions to them.  Finally, we present
a formalization of the problem of learning decomposition methods based
on viewing actions and problems as binary relations on states.



-------