Stability of stochastic delay neural networks

被引:345
作者
Blythe, S [1 ]
Mao, XR [1 ]
Liao, XX [1 ]
机构
[1] Univ Strathclyde, Dept Stat & Modelling Sci, Glasgow G1 1XH, Lanark, Scotland
来源
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS | 2001年 / 338卷 / 04期
基金
英国生物技术与生命科学研究理事会; 英国工程与自然科学研究理事会;
关键词
delay neural network; Brownian motion; martingale convergence theorem; lyapunov; exponent; exponential stability;
D O I
10.1016/S0016-0032(01)00016-3
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The authors in their papers (Liao and Mao, Stochast. Anal. Appl. 14 (2) (1996a) 165-185; Neural, Parallel Sci. Comput. 4 (2) (1996b) 205-244) initiated the study of stability and instability of stochastic neural networks and this paper is the continuation of their research in this area. The main aim of this paper is to discuss almost sure exponential stability for a stochastic delay neural network dx(t) = [-Bx(t) + Ag(x(tau)(t))] dt + sigma (x(t), g(x(tau)(t), t) dw(t). The techniques used in this paper are different from those in their earlier papers. Especially, the nonnegative semimartingale convergence theorem will play an important role in this paper. Several examples are also given for illustration. (C) 2001 The Franklin Institute. Published by Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:481 / 495
页数:15
相关论文
共 19 条
[1]  
[Anonymous], 1994, NEURAL NETWORKS
[2]  
Arnold L., 1972, STOCHASTIC DIFFERENT
[3]  
COBEN MA, 1983, IEEE T SYST MAN CYB, V13, P815
[4]  
Friedman A., 1976, STOCHASTIC DIFFERENT
[5]  
Hasminskii R., 1981, STOCHASTIC STABILITY
[6]   NEURONS WITH GRADED RESPONSE HAVE COLLECTIVE COMPUTATIONAL PROPERTIES LIKE THOSE OF 2-STATE NEURONS [J].
HOPFIELD, JJ .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1984, 81 (10) :3088-3092
[7]   NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].
HOPFIELD, JJ .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558
[8]  
HOPFIELD JJ, 1986, MODEL SCI, V233, P3088
[9]  
Kolmanovskii V., 1992, APPL THEORY FUNCTION
[10]  
LECUN Y, 1989, ADV NEURAL INFORM PR, V1, P141