Multistability of Recurrent Neural Networks with Time-varying Delays and the Piecewise Linear Activation Function

被引：172

作者：

Zeng, Zhigang ^{[1
,2
]}

Huang, Tingwen ^{[3
]}

Zheng, Wei Xing ^{[4
]}

机构：

[1] Huazhong Univ Sci & Technol, Dept Control Sci & Engn, Wuhan 430074, Hubei, Peoples R China

[2] Educ Minist China, Image Proc & Intelligent Control Key Lab, Wuhan 430074, Hubei, Peoples R China

[3] Texas A&M Univ, Doha 5825, Qatar

[4] Univ Western Sydney, Sch Comp & Math, Sydney, NSW 1797, Australia

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2010年 / 21卷 / 08期

基金：

澳大利亚研究理事会;

关键词：

Attractive set; multistability; piecewise linear; time-varying delays; GLOBAL OUTPUT CONVERGENCE; ASSOCIATIVE MEMORIES; STABILITY ANALYSIS; MULTIPERIODICITY; ATTRACTIVITY;

D O I：

10.1109/TNN.2010.2054106

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 brief, stability of multiple equilibria of recurrent neural networks with time-varying delays and the piecewise linear activation function is studied. A sufficient condition is obtained to ensure that n-neuron recurrent neural networks can have (4k - 1)(n) equilibrium points and (2k)(n) of them are locally exponentially stable. This condition improves and extends the existing stability results in the literature. Simulation results are also discussed in one illustrative example.

引用

页码：1371 / 1377

页数：8

共 21 条

[1] DISCRETE-TIME CELLULAR NEURAL NETWORKS FOR ASSOCIATIVE MEMORIES WITH LEARNING AND FORGETTING CAPABILITIES [J].

BRUCOLI, M ;

CARNIMEO, L ;

GRASSI, G .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1995, 42 (07) :396-399

[2] Multistability and multiperiodicity of delayed Cohen-Grossberg neural networks with a general class of activation functions [J].

Cao, Jinde ;

Feng, Gang ;

Wang, Yanyan .

PHYSICA D-NONLINEAR PHENOMENA, 2008, 237 (13) :1734-1749

[3] Multistability in recurrent neural networks [J].

Cheng, Chang-Yuan ;

Lin, Kuang-Hui ;

Shih, Chih-Wen .

SIAM JOURNAL ON APPLIED MATHEMATICS, 2006, 66 (04) :1301-1320

[4] On discrete-time cellular neural networks for associative memories [J].

Grassi, G .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2001, 48 (01) :107-111

[5] On the global output convergence of a class of recurrent neural networks with time-varying inputs [J].

Hu, SQ ;

Liu, DR .

NEURAL NETWORKS, 2005, 18 (02) :171-178

[6] SPARSELY INTERCONNECTED NEURAL NETWORKS FOR ASSOCIATIVE MEMORIES WITH APPLICATIONS TO CELLULAR NEURAL NETWORKS [J].

LIU, D ;

MICHEL, AN .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 1994, 41 (04) :295-307

[7] Global output convergence of a class of continuous-time recurrent neural networks with time-varying thresholds [J].

Liu, DR ;

Hu, SQ ;

Wang, J .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2004, 51 (04) :161-167

[8] QUALITATIVE LIMITATIONS INCURRED IN IMPLEMENTATIONS OF RECURRENT NEURAL NETWORKS [J].

MICHEL, AN ;

WANG, KN ;

LIU, DR ;

YE, H .

IEEE CONTROL SYSTEMS MAGAZINE, 1995, 15 (03) :52-65

[9] Dual-mode space-varying self-designing cellular neural networks for associative memory [J].

Perfetti, R .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1999, 46 (10) :1281-1285

[10] Multistability and New Attraction Basins of Almost-Periodic Solutions of Delayed Neural Networks [J].

Wang, Lili ;

Lu, Wenlian ;

Chen, Tianping .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (10) :1581-1593

← 1 2 3 →