New, Faster Algorithms for Supervised Competitive Learning: Counterpropagation and Adaptive-Resonance Functionality

Authors:
Granino A. Korn
Affiliations:
ECE Department, University of Arizona, Tucson, AZ 7750 South Lakeshore Road, #15, Chelan, WA 68816
Venue:
Neural Processing Letters
Year:
1999

Citing 7
Cited 0

Interactive dynamic system simulation

Interactive dynamic system simulation
Neural networks and natural intelligence

Neural networks and natural intelligence
Neural network models for pattern recognition and associative memory

Neural Networks
Art 2-A: an adaptive resonance algorithm for rapid category learning and recognition

Neural Networks
ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network

Neural Networks
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Neural Networks and Fuzzy-Logic Control on Personal Computers and Workstations

Neural Networks and Fuzzy-Logic Control on Personal Computers and Workstations

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.