Analysis and synthesis of a class of discrete-time neural networks with nonlinear interconnections

Jennie Si, A. N. Michel

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

In the present paper, a qualitative analysis and a synthesis procedure for a class of discrete-time, synchronous neural networks with nonlinear interconnections (of polynomial form) are presented. Networks generated by the present synthesis procedure have, in general, greater memory storage capacity than corresponding networks with a linear interconnecting structure. The qualitative results that constitute the basis of the synthesis procedure include a simple stability test for the equilibrium points of the class of networks considered. Conditions under which such networks are globally stable have not been identified at this time. To simplify the presentation, we confine ourselves to second-order polynomial network interconnections; however, the qualitative results and the synthesis procedure developed herein apply to networks with higher order polynomial interconnections as well.

Original languageEnglish (US)
Pages (from-to)52-58
Number of pages7
JournalIEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
Volume41
Issue number1
DOIs
StatePublished - Jan 1994

Fingerprint

Neural networks
Polynomials
Data storage equipment

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{346d6ffa034b4b3dbafe90d930622fd8,
title = "Analysis and synthesis of a class of discrete-time neural networks with nonlinear interconnections",
abstract = "In the present paper, a qualitative analysis and a synthesis procedure for a class of discrete-time, synchronous neural networks with nonlinear interconnections (of polynomial form) are presented. Networks generated by the present synthesis procedure have, in general, greater memory storage capacity than corresponding networks with a linear interconnecting structure. The qualitative results that constitute the basis of the synthesis procedure include a simple stability test for the equilibrium points of the class of networks considered. Conditions under which such networks are globally stable have not been identified at this time. To simplify the presentation, we confine ourselves to second-order polynomial network interconnections; however, the qualitative results and the synthesis procedure developed herein apply to networks with higher order polynomial interconnections as well.",
author = "Jennie Si and Michel, {A. N.}",
year = "1994",
month = "1",
doi = "10.1109/81.260221",
language = "English (US)",
volume = "41",
pages = "52--58",
journal = "IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications",
issn = "1549-8328",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Analysis and synthesis of a class of discrete-time neural networks with nonlinear interconnections

AU - Si, Jennie

AU - Michel, A. N.

PY - 1994/1

Y1 - 1994/1

N2 - In the present paper, a qualitative analysis and a synthesis procedure for a class of discrete-time, synchronous neural networks with nonlinear interconnections (of polynomial form) are presented. Networks generated by the present synthesis procedure have, in general, greater memory storage capacity than corresponding networks with a linear interconnecting structure. The qualitative results that constitute the basis of the synthesis procedure include a simple stability test for the equilibrium points of the class of networks considered. Conditions under which such networks are globally stable have not been identified at this time. To simplify the presentation, we confine ourselves to second-order polynomial network interconnections; however, the qualitative results and the synthesis procedure developed herein apply to networks with higher order polynomial interconnections as well.

AB - In the present paper, a qualitative analysis and a synthesis procedure for a class of discrete-time, synchronous neural networks with nonlinear interconnections (of polynomial form) are presented. Networks generated by the present synthesis procedure have, in general, greater memory storage capacity than corresponding networks with a linear interconnecting structure. The qualitative results that constitute the basis of the synthesis procedure include a simple stability test for the equilibrium points of the class of networks considered. Conditions under which such networks are globally stable have not been identified at this time. To simplify the presentation, we confine ourselves to second-order polynomial network interconnections; however, the qualitative results and the synthesis procedure developed herein apply to networks with higher order polynomial interconnections as well.

UR - http://www.scopus.com/inward/record.url?scp=0028204644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028204644&partnerID=8YFLogxK

U2 - 10.1109/81.260221

DO - 10.1109/81.260221

M3 - Article

VL - 41

SP - 52

EP - 58

JO - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications

JF - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications

SN - 1549-8328

IS - 1

ER -