Multistability of neural networks with discontinuous activation function

被引：58

作者：

Huang, Gan ^{[1
]}

Cao, Jinde ^{[1
]}

机构：

[1] Southeast Univ, Dept Math, Nanjing 210096, Peoples R China

来源：

COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION | 2008年 / 13卷 / 10期

基金：

中国国家自然科学基金;

关键词：

neural networks; multilevel function; activation function; multistability;

D O I：

10.1016/j.cnsns.2007.07.005

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

In this paper, the multistability is studied for two-dimensional neural networks with multilevel activation functions. And it is showed that the system has n(2) isolated equilibrium points which are locally exponentially stable, where the activation function has n segments. Furthermore, evoked by periodic external input, n(2) periodic orbits which are locally exponentially attractive, can be found. And these results are extended to k-neuron networks, which is really enlarge the capacity of the associative memories. Examples and simulation results are used to illustrate the theory. (c) 2007 Elsevier B.V. All rights reserved.

引用

页码：2279 / 2289

页数：11

共 24 条

[1] Globally exponentially robust stability and periodicity of delayed neural networks [J].

Cao, J ;

Chen, TP .

CHAOS SOLITONS & FRACTALS, 2004, 22 (04) :957-963

[2] Boundedness and stability for Cohen-Grossberg neural network with time-varying delays [J].

Cao, J ;

Liang, JL .

JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2004, 296 (02) :665-685

[3] Global asymptotic and robust stability of recurrent neural networks with time delays [J].

Cao, JD ;

Wang, J .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2005, 52 (02) :417-426

[4] Global robust stability of delayed recurrent neural networks [J].

Cao, JD ;

Huang, DS ;

Qu, YZ .

CHAOS SOLITONS & FRACTALS, 2005, 23 (01) :221-229

[5] Absolute exponential stability of recurrent neural networks with Lipschitz-continuous activation functions and time delays [J].

Cao, JD ;

Wang, J .

NEURAL NETWORKS, 2004, 17 (03) :379-390

[6] 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

[7] A note on neural networks with multiple equilibrium points [J].

Forti, M .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1996, 43 (06) :487-491

[8] Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain [J].

Forti, M ;

Nistri, P ;

Papini, D .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (06) :1449-1463

[9] NEW CONDITIONS FOR GLOBAL STABILITY OF NEURAL NETWORKS WITH APPLICATION TO LINEAR AND QUADRATIC-PROGRAMMING PROBLEMS [J].

FORTI, M ;

TESI, A .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 1995, 42 (07) :354-366

[10] Global convergence of neural networks with discontinuous neuron activations [J].

Forti, M ;

Nistri, P .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2003, 50 (11) :1421-1435

← 1 2 3 →