Title

Properties Of Learning In Artmap

Authors

Authors

M. Georgiopoulos; J. X. Huang;G. L. Heileman

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

Neural Netw.

Keywords

NEURAL NETWORK; PATTERN RECOGNITION; LEARNING; ADAPTIVE RESONANCE; THEORY; ART1; ARTMAP; NEURAL NETWORK; CLASSIFICATION; ARCHITECTURE; ART1; Computer Science, Artificial Intelligence

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 M(a) - 1 list presentations, where M(a) 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 beta(a) values, where beta(a) is a parameter associated with the adaptation of bottom-up weights in one of the ART1 modules of ARTMAP.

Journal Title

Neural Networks

Volume

7

Issue/Number

3

Publication Date

1-1-1994

Document Type

Article

Language

English

First Page

495

Last Page

506

WOS Identifier

WOS:A1994NJ80100008

ISSN

0893-6080

Share

COinS