Properties Of Learning Related To Pattern Diversity In Art1

    Authors

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

    Comments

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

    Abbreviated Journal Title

    Neural Netw.

    Abstract

    In this paper we consider a special class of the ART1 neural network. It is shown that if this network 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 patterns of distinct size in the input list. Other useful properties of the ART1 network, associated with the learning of an arbitrary list of binary input patterns, are also examined. These properties reveal some of the "good" characteristics of the ART1 network when it is used as a tool for the learning of recognition categories.

    Journal Title

    Neural Networks

    Volume

    4

    Issue/Number

    6

    Publication Date

    1-1-1991

    Document Type

    Article

    Language

    English

    First Page

    751

    Last Page

    757

    WOS Identifier

    WOS:A1991GW46500005

    ISSN

    0893-6080

    Share

    COinS