Analysis and Synthesis of a Class of Discrete-Time Neural Networks with Multilevel Threshold Neurons

Jennie Si, Anthony N. Michel

Research output: Contribution to journalArticle

34 Scopus citations

Abstract

In contrast to the usual types of neural networks which utilize two states for each neuron, a class of synchronous discrete-time neural networks with multilevel threshold neurons is developed. A qualitative analysis and a synthesis procedure for the class of neural networks considered herein constitute the principal contributions of this paper. The applicability of the present class of neural networks is demonstrated by means of a gray level image processing example, where each neuron can assume one of sixteen values. When compared to the usual neural networks with two state neurons, networks which are endowed with multilevel neurons will, in general, for a given application, require fewer neurons and thus fewer interconnections. This is an important consideration in VLSI implementation.

Original languageEnglish (US)
Pages (from-to)105-116
Number of pages12
JournalIEEE Transactions on Neural Networks
Volume6
Issue number1
DOIs
StatePublished - Jan 1995

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Analysis and Synthesis of a Class of Discrete-Time Neural Networks with Multilevel Threshold Neurons'. Together they form a unique fingerprint.

  • Cite this