• ISSN 0258-2724
  • CN 51-1277/U
  • EI Compendex
  • Scopus 收录
  • 全国中文核心期刊
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

一类混合时滞复值神经网络的动态行为分析

徐晓惠,  张继业,  赵玲

downloadPDF
文章导航 > 西南交通大学学报  > 2014 >  27(3): 470-476.
徐晓惠, 张继业, 赵玲. 一类混合时滞复值神经网络的动态行为分析[J]. 西南交通大学学报, 2014, 27(3): 470-476. doi: 10.3969/j.issn.0258-2724.2014.03.016
引用本文: 徐晓惠, 张继业, 赵玲. 一类混合时滞复值神经网络的动态行为分析[J]. 西南交通大学学报, 2014, 27(3): 470-476. doi: 10.3969/j.issn.0258-2724.2014.03.016
shu
XU Xiaohui, ZHANG Jiye, ZHAO Ling. Dynamic Behaviors Analysis of a Class of Complex-Valued Neural Networks with Mixed Time Delays[J]. Journal of Southwest Jiaotong University, 2014, 27(3): 470-476. doi: 10.3969/j.issn.0258-2724.2014.03.016
Citation: XU Xiaohui, ZHANG Jiye, ZHAO Ling. Dynamic Behaviors Analysis of a Class of Complex-Valued Neural Networks with Mixed Time Delays[J]. Journal of Southwest Jiaotong University, 2014, 27(3): 470-476. doi: 10.3969/j.issn.0258-2724.2014.03.016
shu

一类混合时滞复值神经网络的动态行为分析

doi: 10.3969/j.issn.0258-2724.2014.03.016
基金项目: 

国家自然科学基金资助项目（11172247，51375402，61273021）

Dynamic Behaviors Analysis of a Class of Complex-Valued Neural Networks with Mixed Time Delays

    摘要
  • 摘要: 为将复值神经网络应用于模式识别，对一类具有混合时滞的复值神经网络平衡点的动态行为进行了探讨.在假定激活函数满足Lipschitz条件的情况下，利用同胚映射相关引理以及向量Lyapunov函数法，研究了确保该系统平衡点的存在性、唯一性以及指数稳定性的充分条件.研究结果表明，用复值神经网络的权系数、自反馈函数及激活函数所构造的判定矩阵是M矩阵.最后，通过一个数值仿真算例验证了所得结论的正确性.

     

    Abstract: To apply the complex-valued neural networks to pattern recognition, the dynamical behaviors of the equilibrium point of a class of complex-valued networks with mixed time delays were investigated. Assuming that the activation functions satisfy the global Lipschitz condition, some sufficient conditions for assuring the existence, uniqueness and exponential stability of the equilibrium point of the system were obtained by using homeomorphism mapping lemma and the vector Lyapunov function methods. The results show that the judgment matrices constructed using weighted coefficients, self-feedback functions and activation functions of the system were M matrix. Finally, a numerical example was presented to show the correctness of the obtained results.

     

    • HTML全文
    • 参考文献(16)
  • LAMPINEN J, VEHTATI A. Bayesian approach for neural networks: review and case studies[J]. Neural Networks, 2001, 14(3): 257-274.
    ZHANG Jiye, SUDA Y, IWASA T. Absolutely exponential stability of a class of neural networks with unbounded delays[J]. Neural Networks, 2004, 17(3): 391-397.
    龙兰, 徐晓惠, 张继业. 时滞Cohen-Grossberg神经网络的全局稳定性[J]. 西南交通大学学报, 2008, 43(3): 381-386. LONG Lan, XU Xiaohui, ZHANG Jiye. Global stability analysis in Cohen-Grossberg neural networks with unbounded time delays[J]. Journal of Southwest Jiaotong University, 2008, 43(3): 381-386.
    SHAO Jinliang, HUANG Tingzhu, ZHOU Sheng. Some improved criteria for global robust exponential stability of neural networks with time-varying delays[J]. Communications in Nonlinear Science and Numerical Simulation, 2010, 15(12): 3782-3794.
    ZHANG Huaguang, WANG Zhanshan, LIU Derong. Global asymptotic stability of recurrent neural networks with multiple time-varying delays[J]. IEEE Trans-actions on Neural Networks, 2008, 19(5): 855-873.
    LIN Da, WANG Xingyuan. Self-organizing adaptive fuzzy neural control for the synchronization of uncertain chaotic systems with random-varying parameters[J]. Neurocomputing, 2011, 74(12/13): 2241-2249.
    HUANG Yujiao, ZHANG Huaguang, WANG Zhanshan. Dynamical stability analysis of multiple equilibrium points in time-varying delayed recurrent neural networks with discontinuous activation functions[J]. Neurocomputing, 2012, 91(1): 21-28.
    BAO Gang, ZENG Zhigang. Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions[J]. Neurocomputing, 2012, 77(1): 101-107.
    ZHU Song, LOU Weiwei, SHEN Yi. Robustness analysis for connection weight matrices of global exponential stability of stochastic recurrent neural networks[J]. Neural Networks, 2013, 38(1): 17-22.
    ENSARI T, ARIK S. New results for robust stability of dynamical neural networks with discrete time delays[J]. Expert Systems with Applications, 2010, 37(8): 5925-5930.
    杨杰, 王直杰, 董宗祥. 复数Hopfield神经网络在路牌识别中的应用[J]. 微计算机信息, 2010, 26(8): 161-163. YANG Jie, WANG Zhijie, DONG Zongxiang. Road sign recognition using complex-valued Hopfield neural network[J]. Microcomputer Information, 2010, 26(8): 161-163.
    SREE H R V, MURTHY G R. Global dynamics of a class of complex valued neural networks[J]. International Journal Neural Systems, 2008, 18(2): 165-171.
    HU Jin, WANG Jun. Global stability of complex-valued recurrent neural networks with time-delays[J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(6): 853-864.
    LEE D Q. Relaxation of the stability condition of the complex-valued neural networks[J]. IEEE Transaction on Neural Networks, 2001, 12(5): 1260-1262.
    LIU Xiaoyu, FANG Kangling, LIU Bin. A synthesis method based on stability analysis for complex-valued Hopfield neural network[C]//Proceedings of the 7th Asian Control Conference. Hong Kong:[s.n], 2009: 1245-1250.
    DUAN Chengjun, SONG Qiankun. Boundedness and stability for discrete-time delayed neural network with complex-valued linear threshold neurons[J]. Discrete Dynamics in Nature and Society, 2010: 368379-1-368379-19.
    • 相关文章
    • 施引文献
  • 附加材料(0)
  • 加载中
WeChat 点击查看大图
计量
  • 文章访问数:  1023
  • HTML全文浏览量:  49
  • PDF下载量:  467
  • 被引次数: 0
出版历程
  • 收稿日期:  2013-05-21
  • 刊出日期:  2014-06-25

目录

    /

    返回文章
    返回

    Copyright © 2009 西南交通大学学报

    地址：四川省成都市郫都区犀安路999号西南交通大学犀浦校区《西南交通大学学报》编辑部

    电话：028-66367562传真：028-66366552Email：xbz@home.swjtu.edu.cn

    本系统由 北京仁和汇智信息技术有限公司 开发 技术支持： info@rhhz.net