Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays

被引:207
作者
Cao, JD [1 ]
Wang, J
机构
[1] Southeast Univ, Dept Math, Nanjing 210096, Peoples R China
[2] Chinese Univ Hong Kong, Dept Automat & Comp Aided Engn, Hong Kong, Hong Kong, Peoples R China
关键词
delayed neural networks; delay Halanay-type inequality absolute exponential stability; additive diagonal stability; partial Lipschitz continuity;
D O I
10.1016/j.neunet.2003.08.007
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper investigates the absolute exponential stability of a general class of delayed neural networks, which require the activation functions to be partially Lipschitz continuous and monotone nondecreasing only, but not necessarily differentiable or bounded. Three new sufficient conditions are derived to ascertain whether or not the equilibrium points of the delayed neural networks with additively diagonally stable interconnection matrices are absolutely exponentially stable by using delay Halanay-type inequality and Lyapunov function. The stability criteria are also suitable for delayed optimization neural networks and delayed cellular neural networks whose activation functions are often nondifferentiable or unbounded. The results herein answer a question: if a neural network without any delay is absolutely exponentially stable, then under what additional conditions, the neural networks with delay is also absolutely exponentially stable. (C) 2003 Elsevier Ltd. All rights reserved.
引用
收藏
页码:379 / 390
页数:12
相关论文
共 36 条
[31]  
Liao TL, 2000, IEEE T NEURAL NETWOR, V11, P1481, DOI 10.1109/72.883480
[32]   STABILITY OF ANALOG NEURAL NETWORKS WITH DELAY [J].
MARCUS, CM ;
WESTERVELT, RM .
PHYSICAL REVIEW A, 1989, 39 (01) :347-359
[33]   Bifurcations, stability, and monotonicity properties of a delayed neural network model [J].
Olien, L ;
Belair, J .
PHYSICA D, 1997, 102 (3-4) :349-363
[34]   Effect of delay on the boundary of the basin of attraction in a system of two neurons [J].
Pakdaman, K ;
Grotta-Ragazzo, C ;
Malta, CP ;
Arino, O ;
Vibert, JF .
NEURAL NETWORKS, 1998, 11 (03) :509-519
[35]  
SANDBERG IW, 1969, AT&T TECH J, V48, P1
[36]   EXPONENTIAL STABILITY AND A SYSTEMATIC SYNTHESIS OF A NEURAL NETWORK FOR QUADRATIC MINIMIZATION [J].
SUDHARSANAN, SI ;
SUNDARESHAN, MK .
NEURAL NETWORKS, 1991, 4 (05) :599-613