Title

The N-N-N Conjecture In Art1

Authors

M Georgiopoulos

Title - Alternative

Acta Mech.

Keywords

NEURAL NETWORK; PATTERN RECOGNITION; SELF-ORGANIZATION; LEARNING; ADAPTIVE RESONANCE THEORY; ART1; Computer Science, Artificial Intelligence

Abstract

In this paper we consider the ART1 neural network architecture introduced by Carpenter and Grossberg. In their original paper, Carpenter and Grossberg made the following conjecture: In the fast learning case, if the F2 layer in ART1 has at least N nodes, then each member of a list of N input patterns presented cyclically at the F1 layer of ART1 will have direct access to an F2 layer node after at most N list presentations. In this paper, we demonstrate that the conjecture is not valid for certain large L values, where L is a network parameter associated with the adaptation of the bottom-up traces in ART1. It is worth noting that previous work has shown the conjecture to be true for small L values.

Publication Title

Acta Mechanica

Volume

93

Issue/Number

5

Publication Date

1-1-1992

Document Type

Article

Language

English

First Page

745

Last Page

753

WOS Identifier

WOS:A1992HV28200014

ISSN

0893-6080

Share

COinS