Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Strategy Learning with Multilayer Connectionist Representations 1
 

Summary: Strategy Learning with Multilayer
Connectionist Representations 1
Charles W. Anderson
Department of Computer Science
Colorado State University
Fort Collins, CO 80523
anderson@cs.colostate.edu
http: www.cs.colostate.edu ~anderson
Abstract
Results are presented that demonstrate the learning and ne-tuning of search strategies using connectionist
mechanisms. Previous studies of strategy learning within the symbolic, production-rule formalism have not
addressed ne-tuning behavior. Here a two-layer connectionist system is presented that develops its search from
a weak to a task-speci c strategy and ne-tunes its performance. The system is applied to a simulated, real-
time, balance-control task. We compare the performance of one-layer and two-layer networks, showing that the
ability of the two-layer network to discover new features and thus enhance the original representation is critical
to solving the balancing task.
1. Introduction
A strategy is a method for guiding the search for a solution to a problem, where a solution typically
consists of a sequence of actions. Most research on the learning of strategies has used symbolic forms of
representation, such as production rules, which have been useful in modeling some of the conscious steps

  

Source: Anderson, Charles W. - Department of Computer Science, Colorado State University

 

Collections: Computer Technologies and Information Sciences