Absolute periodicity and absolute stability of delayed neural networks

被引：82
作者：
Yi, Z [1 ]
Heng, PA
Vadakkepat, P
机构：
[1] Chinese Univ Hong Kong, Dept Comp Sci & Engn, Shatin, Hong Kong, Peoples R China
[2] Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 119260, Singapore
来源：
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS | 2002年 / 49卷 / 02期
关键词：
absolute periodicity; absolute stability; delay; neural networks;
D O I：
10.1109/81.983875
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：
In this brief. we propose to study the absolute periodicity of delayed neural networks. A neural network is said to be absolutely periodic, if for every activation function in some suitable functional set and every input periodic vector function, a unique periodic solution of the network exists and all other solutions of the network converge exponentially to it. Absolute stability of delayed neural networks is also studied in this paper. Simple and checkable conditions for guaranteeing absolute periodicity and absolute stability are derived. Simulations for absolute periodicity are given.
引用
收藏
页码：256 / 261
页数：6
相关论文
共 25 条
[1]   A comment on "Comments on 'Necessary and sufficient condition for absolute stability of neural networks'" [J].
Liang, XB ;
Wu, LD .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1998, 45 (05) :594-594
[2]   On the global asymptotic stability of delayed cellular neural networks [J].
Arik, S ;
Tavsanoglu, V .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2000, 47 (04) :571-574
[3]   A sufficient condition for absolute stability of a larger class of dynamical neural networks [J].
Arik, S ;
Tavsanoglu, V .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2000, 47 (05) :758-760
[4]   Stability analysis of delayed neural networks [J].
Arik, S .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2000, 47 (07) :1089-1092
[5]   HOW DELAYS AFFECT NEURAL DYNAMICS AND LEARNING [J].
BALDI, P ;
ATIYA, AF .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (04) :612-621
[6]  
Berman A., 1994, CLASSICS APPL MATH, DOI [10.1016/C2013-0-10361-3, 10.1137/1.9781611971262, DOI 10.1137/1.9781611971262]
[7]   Neurocomputing with time delay analysis for solving convex quadratic programming problems [J].
Chen, YH ;
Fang, SC .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (01) :230-240
[8]   ON STABILITY OF CELLULAR NEURAL NETWORKS WITH DELAY [J].
CIVALLERI, PP ;
GILLI, M ;
PANDOLFI, L .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1993, 40 (03) :157-165
[9]   NECESSARY AND SUFFICIENT CONDITION FOR ABSOLUTE STABILITY OF NEURAL NETWORKS [J].
FORTI, M ;
MANETTI, S ;
MARINI, M .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1994, 41 (07) :491-494
[10]   STABILITY OF CELLULAR NEURAL NETWORKS AND DELAYED CELLULAR NEURAL NETWORKS WITH NONPOSITIVE TEMPLATES AND NONMONOTONIC OUTPUT FUNCTIONS [J].
GILLI, M .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 1994, 41 (08) :518-528
123