Paper Info
Title
Distributed learning, recognition, and prediction by ART and ARTMAP neural networks
Abstract
A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dART reduces to fuzzy ART and the supervised model dARTMAP reduces to fuzzy ARTMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. Distributed ART models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match-reset-search process also helps stabilize memory. Without the match-reset-search system, dART becomes a type of distributed competitive learning network. (C) 1997 Elsevier Science Ltd.
Year
DOI
Venue
1997
10.1016/S0893-6080(97)00004-X
Neural Networks
Keywords
DocType
Volume
adaptive resonance theory,adaptive thresholding,competitive learning,winner take all,long term potentiation,neural network,long term depression,low frequency,multilayer perceptron
Journal
10
Issue
ISSN
Citations 
9
0893-6080
57
PageRank 
References 
Authors
5.46
19
1
Name
Order
Citations
PageRank
Gail A. Carpenter12909760.83