Properties Of Learning In Artmap

    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