Title
The N-N-N Conjecture In Art1
Keywords
Adaptive resonance theory; ART1; Learning; Neural network; Pattern recognition; Self-organization
Abstract
In this paper we consider the ART1 neural network architecture introduced by Carpenter and Grossberg. In their original paper, Carpenter and Grossberg made the following conjecture: In the fast learning case, if the F2 layer in ART1 has at least N nodes, then each member of a list of N input patterns presented cyclically at the F1 layer of ART1 will have direct access to an F2 layer node after at most N list presentations. In this paper, we demonstrate that the conjecture is not valid for certain large L values, where L is a network parameter associated with the adaptation of the bottom-up traces in ART1. It is worth noting that previous work has shown the conjecture to be true for small L values. © 1992 Pergamon Press Ltd.
Publication Date
1-1-1992
Publication Title
Neural Networks
Volume
5
Issue
5
Number of Pages
745-753
Document Type
Article
Identifier
scopus
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/S0893-6080(05)80135-2
Copyright Status
Unknown
Socpus ID
0026923906 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0026923906
STARS Citation
Georgiopoulos, Michael; Heileman, Gregory L.; and Huang, Juxin, "The N-N-N Conjecture In Art1" (1992). Scopus Export 1990s. 1101.
https://stars.library.ucf.edu/scopus1990/1101