Tech. Report - Task Rehearsal Method of Sequential Learning
Daniel L. Silver
dsilver at mgmt.dal.ca
Fri Feb 20 18:17:40 EST 1998
Dear colleagues,
the following TR is now available:
"The Task Rehearsal Method of Sequential Learning"
Department of Computer Science
Univeristy of Western Ontario
Technical Report # 517
Daniel L. Silver and Robert E. Mercer
Abstract
An hypothesis of functional transfer of task knowledge is presented
that requires the development of a measure of task relatedness and a
method of sequential learning. The "task rehearsal method" (TRM) is
introduced to address the issues of sequential learning, namely
retention and transfer of knowledge. TRM is a knowledge based
inductive learning system that uses functional domain knowledge as a
source of inductive bias. The representations of successfully learned
tasks are stored within domain knowledge. "Virtual examples" generated
by domain knowledge are rehearsed in parallel with the each new task
using either the standard multiple task learning (MTL) or the $\eta$MTL
neural network methods. The results of experiments conducted on a
synthetic domain of seven tasks demonstrate the method's ability
to retain and transfer task knowledge. TRM is shown to be effective
in developing hypothesis for tasks that suffer from impoverished
training sets. Difficulties encountered during sequential learning
over the diverse domain reinforce the need for a more robust measure
of task relatedness.
----------------------------------------------------------------------
Comments are welcome!
Download sites:
http://www.csd.uwo.ca/~dsilver/trmpaper.ps
or
http://www.csd.uwo.ca/~dsilver/trmpaper.ps.Z
//////////////////////////////////////////////////////////////////////
Daniel L. Silver
CogNova Technologies Phone: (902) 582-7558
1226 J.Jordan Road Fax: (902) 582-3140
Canning,Nova Scotia Dal.U: (902) 494-1813
Canada B0P 1H0 Email: dsilver at mgmt.dal.ca
Homepage: http://www.meadoworks.ns.ca/cognova
///////////////////////////////////////////////////////////////
More information about the Connectionists
mailing list