Title
Properties Of Learning In Art1
Abstract
The authors consider the ART1 neural network architecture. Useful properties of ART1, associated with the learning of an arbitrary list of binary input patterns, are examined. These properties reveal some of the good characteristics of the ART1 neural network architecture when it is used as a tool for the learning of recognition categories. In particular, it was found that if ART1 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 distinct size patterns in the input list.
Publication Date
12-1-1991
Number of Pages
2671-2676
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
0026297704 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0026297704
STARS Citation
Georgiopoulos, Michael; Heileman, Gregory L.; and Huang, Juxin, "Properties Of Learning In Art1" (1991). Scopus Export 1990s. 1205.
https://stars.library.ucf.edu/scopus1990/1205