SHUNTING INHIBITORY CELLULAR NEURAL NETWORKS - DERIVATION AND STABILITY ANALYSIS

被引：141

作者：

BOUZERDOUM, A ^{[1
]}

PINTER, RB ^{[1
]}

机构：

[1] UNIV WASHINGTON,DEPT ELECT ENGN,SEATTLE,WA 98195

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS | 1993年 / 40卷 / 03期

关键词：

D O I：

10.1109/81.222804

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, a class of biologically inspired cellular neural networks is introduced. These networks possess lateral interactions of the shunting inhibitory type only; hence, they are called shunting inhibitory cellular neural networks (SICNN's). Their derivation and biophysical interpretation are presented in this article, along with a stability analysis of their dynamics. In particular, it is shown that the SICNN's are bounded input bounded output stable dynamical systems. Furthermore, a global Liapunov function is derived for symmetric SICNN's. Using LaSalle invariance principle, it is shown that each trajectory converges to a set of equilibrium points; this set consists of a unique equilibrium point if all inputs have the same polarity.

引用

页码：215 / 221

页数：7

共 41 条

[1]

BOUZERDOUM A, 1991, SENSORY NEURAL NETWO, P47

[2]

BOUZERDOUM A, 1991, THESIS U WASHINGTON

[3]

BOUZERDOUM A, 1989, SPIE1199, P1229

[4]

BOUZERDOUM A, 1991, SPIE1473, P29

[5]

BOUZERDOUM A, 1990, P INT JOINT C NEURAL

[6]

Bouzerdoum A, 1992, NONLINEAR VIS, P423

[7]

BOUZERDOUM A, 1993, IN PRESS PHIL T R SO

[8] THE ART OF ADAPTIVE PATTERN-RECOGNITION BY A SELF-ORGANIZING NEURAL NETWORK [J].

CARPENTER, GA ;

GROSSBERG, S .

COMPUTER, 1988, 21 (03) :77-88

[9] CELLULAR NEURAL NETWORKS - APPLICATIONS [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290

[10] CELLULAR NEURAL NETWORKS - THEORY [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272

← 1 2 3 4 5 →