archives

Toward Learning Systems That Integrate Different Strategies and Representations


Home 

About 

Browse 

Search 

Register 

Subscriptions 

Deposit Papers 

Help
    

Honavar, Vasant (1993) Toward Learning Systems That Integrate Different Strategies and Representations. Technical Report TR93-22, Department of Computer Science, Iowa State University.

Full text available as:Postscript
Adobe PDF

Abstract

Toward Learning Systems That Integrate Different Strategies and Representations
Vasant Honavar
Department of Computer Science
226 Atanasoff Hall
Iowa State University
Ames, Iowa 50011-1040
honavar@iastate.edu
Technical Report 93-22, September 1993
This is a draft of a chapter to be included in:
Symbol Processors and Connectionist Networks for Artificial Intelligence
and Cognitive Modelling: Steps toward Principled Integration
Honavar, V., & Uhr, L. (ed)., New York: Academic Press (1994).
Abstract
An understanding of learning -- the process by which a learner
acquires and refines a broad range of knowledge and skills -- is central to
the enterprise of building truly adaptive, flexible, robust, and creative
intelligent systems. Significant theoretical and empirical contributions to
the characterization of learning in computational terms have emerged from
research in a number of disparate research paradigms. The limitations of
individual paradigms and of particular classes of techniques within each
paradigm are beginning to be recognized.  Converging lines of evidence from
multiple sources, both theoretical as well as empirical, suggest that
artificial intelligence systems, in order to be able to deal with complex
tasks such as recognizing and describing 3-dimensional objects, or
communicating in  natural language, must be able to effectively utilize a
range of learning algorithms operating with an adequate repertoire of
representational structures. This paper draws on a broad range of research
on learning in artificial intelligence, connectionist networks, statistical
and syntactic methods in pattern recognition, and evolutionary models to
identify the similarities and differences among, strengths and limitations of,
and promising areas for cross-fertilization between, the different paradigms.
_______________________________________________________________________
This work was partially supported by the Iowa State University College of
Liberal Arts and Sciences.

Subjects:All uncategorized technical reports
ID code:00000056
Deposited by:Staff Account on 21 October 1993



Contact site administrator at: ssg@cs.iastate.edu