ON STABILITY OF CELLULAR NEURAL NETWORKS WITH DELAY

被引：280

作者：

CIVALLERI, PP ^{[1
]}

GILLI, M ^{[1
]}

PANDOLFI, L ^{[1
]}

机构：

[1] POLITECN TORINO, DIPARTIMENTO MATEMAT, I-10129 TURIN, ITALY

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS | 1993年 / 40卷 / 03期

关键词：

D O I：

10.1109/81.222796

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：

It is known that symmetric cellular neural networks (CNN's) are completely stable. In this paper it is shown that CNN's with delay (DCNN's), though symmetric, can become unstable if the delay if suitably chosen: actually such networks can exhibit periodic cycles. Moreover, a sufficient condition is presented to ensure complete stability: such a condition establishes a relation between the delay time and the parameters of the network.

引用

页码：157 / 165

页数：9

共 13 条

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

CHUA, LO ;

YANG, L .

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

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

CHUA, LO ;

YANG, L .

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

[3] STABILITY OF A CLASS OF NONRECIPROCAL CELLULAR NEURAL NETWORKS [J].

CHUA, LO ;

ROSKA, T .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1990, 37 (12) :1520-1527

[4]

CHUA LO, 1990, P 1990 IEEE INT WORK, P12

[5]

CHUA LO, 1991, UNIVERSE STABLE CNN

[6]

HALE J, 1977, THEORY FUNCTIONAL DI

[7] CONVERGENT ACTIVATION DYNAMICS IN CONTINUOUS-TIME NETWORKS [J].

HIRSCH, MW .

NEURAL NETWORKS, 1989, 2 (05) :331-349

[8] SYSTEMS OF DIFFERENTIAL-EQUATIONS THAT ARE COMPETITIVE OR COOPERATIVE .2. CONVERGENCE ALMOST EVERYWHERE [J].

HIRSCH, MW .

SIAM JOURNAL ON MATHEMATICAL ANALYSIS, 1985, 16 (03) :423-439

[9]

KATO T, 1976, PERTURBATION THEORY, P28

[10]

Reissig R., 1974, NONLINEAR DIFFERENTI

← 1 2 →