A survey of learning results in ART architectures

M. Georgiopoulos, J. Huang, G. L. Heileman

Research output: Contribution to journalConference articlepeer-review

Abstract

In this paper we investigate, in unison, the learning properties of ART1, Fuzzy ART and ARTMAP architectures. These architectures were introduced by Carpenter and Grossberg over a time period spanning the last eight years. Some of the learning properties discussed in this paper involve characteristics of the clusters formed in these architectures, while other learning properties concentrate on how fast it will take these architectures to converge to a solution for the type of problems that are capable of solving. This latter issue is a very important issue in the neural network literature, and there are very few instances where it has been answered satisfactorily.

Original languageEnglish (US)
Pages (from-to)416-424
Number of pages9
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume2492
DOIs
StatePublished - Apr 6 1995
Externally publishedYes
EventApplications and Science of Artificial Neural Networks 1995 - Orlando, United States
Duration: Apr 17 1995Apr 21 1995

Keywords

  • ART
  • Learning
  • Neural networks
  • Performance
  • Training

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A survey of learning results in ART architectures'. Together they form a unique fingerprint.

Cite this