Stability analysis of recurrent neural networks with piecewise constant argument of generalized type

被引:55
作者
Akhmet, M. U. [1 ]
Arugaslan, D. [3 ]
Yilmaz, E. [2 ]
机构
[1] Middle E Tech Univ, Dept Math, TR-06531 Ankara, Turkey
[2] Middle E Tech Univ, Inst Appl Math, TR-06531 Ankara, Turkey
[3] Suleyman Demirel Univ, Dept Math, TR-32260 Isparta, Turkey
关键词
Neural networks; Piecewise constant argument of generalized type; Method of Lyapunov functions; GLOBAL EXPONENTIAL STABILITY; TIME-VARYING DELAYS; DIFFERENTIAL-EQUATIONS; ASYMPTOTIC STABILITY; PERIODIC-SOLUTIONS; TRAVELING-WAVES;
D O I
10.1016/j.neunet.2010.05.006
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we apply the method of Lyapunov functions for differential equations with piecewise constant argument of generalized type to a model of recurrent neural networks (RNNs). The model involves both advanced and delayed arguments. Sufficient conditions are obtained for global exponential stability of the equilibrium point. Examples with numerical simulations are presented to illustrate the results. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码:805 / 811
页数:7
相关论文
共 56 条