Properties of learning in ARTMAP

Michael Georgiopoulos, Juxin Huang, Gregory L. Heileman

Research output: Contribution to journalArticlepeer-review

19 Scopus citations

Abstract

In this paper we consider the ARTMAP architecture for situations requiring learning of many-to-one maps. It is shown that if ARTMAP is repeatedly presented with a list of input/output pairs, it establishes the required mapping in at most Ma-1 list presentations, where Ma corresponds to the total number of ones in each one of the input patterns. Other useful properties, associated with the learning of the mapping represented by an arbitrary list of input/output pairs, are also examined. These properties reveal some of the characteristics of learning in ARTMAP when it is used as a tool in establishing an arbitrary mapping from a binary input space to a binary output space. The results presented in this paper are valid for the fast learning case, and for small βa values, where βa is a parameter associated with the adaptation of bottom-up weights in one of the ART1 modules of ARTMAP.

Original languageEnglish (US)
Pages (from-to)495-506
Number of pages12
JournalNeural Networks
Volume7
Issue number3
DOIs
StatePublished - 1994
Externally publishedYes

Keywords

  • ART1
  • ARTMAP
  • Adaptive resonance theory
  • Learning
  • Neural network
  • Pattern recognition

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

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

Cite this