Exponential stability of periodic solutions of recurrent neural networks with functional dependence on piecewise constant argument

被引:5
作者
Akhmet, Marat [1 ]
Arugaslan Cincin, Duygu [2 ]
Cengiz, Nur [3 ]
机构
[1] Middle East Tech Univ, Dept Math, Ankara, Turkey
[2] Suleyman Demirel Univ, Dept Math, Isparta, Turkey
[3] Suleyman Demirel Univ, Grad Sch Nat & Appl Sci, Isparta, Turkey
关键词
Recurrent neural networks; functional differential equations; piecewise constant argument; periodic solution; stability; RETARDED DIFFERENTIAL-EQUATIONS; DELAY;
D O I
10.3906/mat-1606-138
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
In this study, we develop a model of recurrent neural networks with functional dependence on piecewise constant argument of generalized type. Using the theoretical results obtained for functional differential equations with piecewise constant argument, we investigate conditions for existence and uniqueness of solutions, bounded solutions, and exponential stability of periodic solutions. We provide conditions based on the parameters of the model.
引用
收藏
页码:272 / 292
页数:21
相关论文
共 25 条