Properties of learning in ART1

Michael Georgiopoulos, Gregory L. Heileman, Juxin Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publication91 IEEE Int Jt Conf Neural Networks IJCNN 91
PublisherPubl by IEEE
Pages2671-2676
Number of pages6
ISBN (Print)0780302273
StatePublished - 1991
Externally publishedYes
Event1991 IEEE International Joint Conference on Neural Networks - IJCNN '91 - Singapore, Singapore
Duration: Nov 18 1991Nov 21 1991

Publication series

Name91 IEEE Int Jt Conf Neural Networks IJCNN 91

Other

Other1991 IEEE International Joint Conference on Neural Networks - IJCNN '91
CitySingapore, Singapore
Period11/18/9111/21/91

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Properties of learning in ART1'. Together they form a unique fingerprint.

Cite this