New, faster algorithms for supervised competitive learning : Counterpropagation and adaptive-resonance functionality

Hecht-Nielsen's counterpropagation networks often learn to associate input and output patterns more quickly than backpropagation networks. But simple competitive learning cannot separate closely spaced input patterns without adaptive-resonance-like (ART) functionality which prevents neighboring...

Full description

Saved in:
Bibliographic Details
Published in:Neural processing letters 1999-04, Vol.9 (2), p.107-117
Main Author: KORN, G. A
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Back propagation networks
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Learning and adaptive systems
Resonance
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hecht-Nielsen's counterpropagation networks often learn to associate input and output patterns more quickly than backpropagation networks. But simple competitive learning cannot separate closely spaced input patterns without adaptive-resonance-like (ART) functionality which prevents neighboring patterns from ‘stealing’ each other's templates. We demonstrate ‘pseudo-ART’ functionality with a new, simple, and very fast algorithm which requires no pattern normalization at all. Competition can be based on either Euclidean or L1-norm matching. In the latter case, the new algorithm emulates fuzzy ART. We apply the pseudo-ART scheme to several new types of counterpropagation networks, including one based on competition among combined input/output patterns, and discuss application with and without noise.
ISSN:1370-4621
1573-773X
DOI:10.1023/A:1018665006640