Title
Properties Of Learning Related To Pattern Diversity In Art1
Keywords
Adaptive resonance theory; ART1; Learning; Neural network; Pattern recognition; Self-organization
Abstract
In this paper we consider a special class of the ART1 neural network. It is shown that if this network is repeatedly presented with an arbitrary list of binary input patterns, learning self-stabilizes in at most m list presentations, where m corresponds to the number of patterns of distinct size in the input list. Other useful properties of the ART1 network, associated with the learning of an arbitrary list of binary input patterns, are also examined. These properties reveal some of the "good" characteristics of the ART1 network when it is used as a tool for the learning of recognition categories. © 1991.
Publication Date
1-1-1991
Publication Title
Neural Networks
Volume
4
Issue
6
Number of Pages
751-757
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/0893-6080(91)90055-A
Copyright Status
Unknown
Socpus ID
0026392741 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0026392741
STARS Citation
Georgiopoulos, Michael; Heileman, Gregory L.; and Huang, Juxin, "Properties Of Learning Related To Pattern Diversity In Art1" (1991). Scopus Export 1990s. 1342.
https://stars.library.ucf.edu/scopus1990/1342