广西师范大学学报（自然科学版） ›› 2011, Vol. 29 ›› Issue (1): 29-34.

• • 上一篇    下一篇

一类时滞递归神经网络模型的周期振动性

赵慧炜1, 李文华1, 冯春华1, 罗晓曙2   

  1. 1.广西师范大学数学科学学院,广西桂林541004;
    2.广西师范大学电子工程学院,广西桂林541004
  • 收稿日期:2010-10-16 发布日期:2018-11-16
  • 通讯作者: 冯春华(1949—),男,广西荔浦人,广西师范大学教授,博士。E-mail: chfeng@mailbox.gxnu.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(10961005)

Periodic Oscillation Analysis for a Recurrent Neural NetworksModel with Time Delays

ZHAO Hui-wei1, LI Wen-hua1, FENG Chun-hua1, LUO Xiao-shu2   

  1. 1.College of Mathematical Science,Guangxi Normal University,Guilin Guangxi 541004,China;
    2.College of Electronic Engineering,Guangxi Normal University,Guilin Guangxi 541004,China
  • Received:2010-10-16 Published:2018-11-16

摘要： 利用线性矩阵不等式方法,研究一类5个神经元时滞递归神经网络模型的周期振动性,得出保证系统存在周期振动性的一组充分条件,理论分析和数值仿真显示,所得结果为一类5个神经元时滞递归神经网络模型提供了新的振动性判定准则。

关键词: 递归神经网络, 时滞, 周期振动性, 线性矩阵不等式

Abstract: The existence of periodic oscillationsfor a five-neuron recurrent neural network with time delay between neural interconnections is investigated.New criteria are proposed to guarantee the existenceof periodic oscillations for network model.Numerical simulation validates thismethod and demonstrates the correctness of theoretical analysis.

Key words: recurrent neural networks, dealys, periodic oscillation, LMI

中图分类号: 

  • O175.1
[1] RUIZ A,OWENS D H,TOWNLEY S.Existence,learning,and replication of periodic motion in recurrent neural networks[J].IEEE Transactions on Neural Networks,1998,9(4):651-661.
[2] TOWNLEY S,ILCHMANN A,WEISSM G,et al.Existence and learning of oscillations in recurrent neural networks[J].IEEE Transactions on Neural Networks,2000,11(1):205-214.
[3] BéLAIR J,CAMPBELL S A,van den DRIESSCHE P.Frustration stabilityand delay-induced oscillations in a neural network model[J].SIAM J Appl Math,1996,56(1):245-255.
[4] YU Wen-wu,CAO Jin-de.Stability and Hopf bifurcations on a two-neuron system with time delay in the frequency domain[J].Int J Bifur Chaos,2007,17(4):1355-1366.
[5] FENG C,PLAMONDON R.Existence of oscillations in recurrent neuralnetworks with time delay models[J].DCDIS A Suppl Adv Neural Networks,2007,14(S1):111-118.
[6] GAO B,ZHANG Wei-nian.Equilibria and their bifurcations in a recurrent neural network involving iterates of a transcendental function[J].IEEETransactions on Neural Networks,2008,19(5):782-794.
[7] FENG Chun-hua,O'REILLY C,PLAMONDON R.Permanent oscillations in a3-node recurrent neural network model[J].Neurocomputing,2010,74(1/3):274-283.
[8] HALE J.Theory of functional differential equations[M].New York:Springer-Verlag,1977:21-24.
[9] FORTI M,TESI A.New conditions for global stability of neural networks with application to linear and quadratic programming problems[J].IEEE Transactions on Circuits and Systems Ⅰ:Fundamental Theory and Applications,1995,42(7):354-366.
[10] CHAFEE N.A bifurcation problem for a functional differential equation of finitely retarded type[J].Journal of Mathematical Analysis and Applications,1971,35(2):312-348.
[1] 罗兰, 周楠, 司杰. 不确定细胞神经网络鲁棒稳定新的时滞划分法[J]. 广西师范大学学报（自然科学版）, 2019, 37(4): 45-52.
[2] 张一进. Xρ空间上随机时滞格系统的随机动力学[J]. 广西师范大学学报（自然科学版）, 2019, 37(3): 106-110.
[3] 闫荣君, 韦煜明, 冯春华. 带p-Laplacian算子的时滞分数阶微分方程边值问题3个正解的存在性[J]. 广西师范大学学报（自然科学版）, 2017, 35(3): 75-82.
[4] 罗颜涛, 张龙, 滕志东. 一类间歇时滞扩散的概周期捕食系统的持久性[J]. 广西师范大学学报（自然科学版）, 2017, 35(2): 50-57.
[5] 薛晋栋, 冯春华. 一类时滞脉冲微积分方程的正概周期解[J]. 广西师范大学学报（自然科学版）, 2012, 30(4): 48-53.
[6] 冯春华. 一类含n个时滞神经网络模型解的周期振动性[J]. 广西师范大学学报（自然科学版）, 2012, 30(3): 48-53.
[7] 郝平平, 冯春华. 一类具有非线性物种密度制约死亡率的Nicholson模型解的性态[J]. 广西师范大学学报（自然科学版）, 2012, 30(2): 42-47.
[8] 韦煜明, 王勇, 唐艳秋, 范江华. 具p-Laplacian算子时滞微分方程边值问题解的存在唯一性[J]. 广西师范大学学报（自然科学版）, 2012, 30(2): 48-53.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发