Properties of learning related to pattern diversity in ART1

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...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 1991, Vol.4 (6), p.751-757
Hauptverfasser:	Georgiopoulos, Michael, Heileman, Gregory L., Huang, Juxin
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptive resonance theory Applied sciences ART1 Artificial intelligence Computer science control theory systems Exact sciences and technology Learning Neural network Pattern recognition Pattern recognition. Digital image processing. Computational geometry Self-organization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!