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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
S. Grossberg, The Adaptive Brain (2 vols.),North Holland, New York, 1987.
S. Grosberg, NeuralNetworks and Natural Intelligence, MIT Press: Cambridge, MA, 1988. Contains a review of earlier work on ART 1.
G.A. Carpenter, Neural-network models for pattern recognition and associative memory, Neural Networks 2, 243–257, 1990. This is a useful review of earlier work.
G.A. Carpenter et al., ART-2A,Neural Networks 4, 493–504, 1991.
G.A. Carpenter, Fuzzy ART, Neural Networks 4, 759–771, 1991.
G.A. Korn, Interactive statistical experiments withtemplate-matching Neural Networks, IEEE Trans. On Systems, Man, and Cybernetics 20, 1146–1152, 1990.
G.A. Korn,Neural Networks and Fuzzy-logic Control on Personal Computers and Workstations, MIT Press: Cambridge, MA, 1995.
G.A. Korn, Interactive neural-network simulation: a textbook pattern-recognition problem yields to ART-enhanced counterpropagation, Computers in Engineering Education 3, 79–88, 1995.
G.A. Korn, New algorithm for fast adaptive-resonannceemulation (in print), 1997.
G.A. Carpenter et al.,ARTMAP, Neural Networks 4, 565–588, 1991.
G.A. Carpenter, Fuzzy ARTMAP, IEEE Trans. NeuralNetworks 3, 698–713, 1992.
G.A. Korn,Interactive Dynamic System Simulation under Windows 95 and NT, Gordon and Breach, London, 1998.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Korn, G.A. New, Faster Algorithms for Supervised Competitive Learning: Counterpropagation and Adaptive-Resonance Functionality. Neural Processing Letters 9, 107–117 (1999). https://doi.org/10.1023/A:1018665006640
Issue Date:
DOI: https://doi.org/10.1023/A:1018665006640