On threshold functions and multi-valued networks

Document Type

Conference Proceeding

Publication Date

12-1-1992

Abstract

The binary order Hopfield neural network of multi-valued neurons is proposed. An energy function is proposed for synchronous and asynchronous operations. The convergence of this type of network is verified and the upper bounds of convergence time are studied. The number of threshold functions for multi-valued neurons is investigated. The enhancement of memory capacity is also discussed.

Identifier

0027105358 (Scopus)

Publication Title

Intelligent Engineering Systems Through Artificial Neural Networks

First Page

73

Last Page

78

Volume

2

This document is currently not available here.

Share

COinS