留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于忆阻的时滞神经网络的全局稳定性

胡进 宋乾坤

胡进, 宋乾坤. 基于忆阻的时滞神经网络的全局稳定性[J]. 应用数学和力学, 2013, 34(7): 724-735. doi: 10.3879/j.issn.1000-0887.2013.07.007
引用本文: 胡进, 宋乾坤. 基于忆阻的时滞神经网络的全局稳定性[J]. 应用数学和力学, 2013, 34(7): 724-735. doi: 10.3879/j.issn.1000-0887.2013.07.007
HU Jin, SONG Qian-kun. Global Uniform Asymptotic Stability of Memristor-Based Recurrent Neural Networks With Time Delays[J]. Applied Mathematics and Mechanics, 2013, 34(7): 724-735. doi: 10.3879/j.issn.1000-0887.2013.07.007
Citation: HU Jin, SONG Qian-kun. Global Uniform Asymptotic Stability of Memristor-Based Recurrent Neural Networks With Time Delays[J]. Applied Mathematics and Mechanics, 2013, 34(7): 724-735. doi: 10.3879/j.issn.1000-0887.2013.07.007

基于忆阻的时滞神经网络的全局稳定性

doi: 10.3879/j.issn.1000-0887.2013.07.007
基金项目: 国家自然科学基金资助项目(61273021);重庆市自然科学基金重点项目(CQcstc2013jjB40008)
详细信息
    作者简介:

    胡进(1980—),男,湖北襄阳人, 讲师,博士(E-mail: victorjhu@gmail.com);宋乾坤(1963—),男,教授,博士(通讯作者. E-mail:qiankunsong@163.com).

  • 中图分类号: O175.13

Global Uniform Asymptotic Stability of Memristor-Based Recurrent Neural Networks With Time Delays

  • 摘要: 忆阻是近年来新发现的一类非线性电子元件.与通常的电阻不同,忆阻的阻值会随着通过的电流量的大小和方向不同而改变.这个特性使得忆阻具有了记忆的功能,在很多方面有着广泛的应用.该文给出了简化的忆阻的数学模型,基于该模型构造了时滞神经网络,利用微分包含理论、Lyapunov方法和同胚映射原理研究了其全局渐近稳定性问题,确保模型平衡点存在性、唯一性和一致全局渐近稳定性的充分条件被获得.最后提供的具有仿真的例子验证了获得的理论结果.
  • [1] Strukov D B, Snider G S, Stewart D R, Williams R S. The missing memristor found[J].Nature,2008, 453(7191): 80-83.
    [2] Chua L O. Memristor the missing circuit element[J].IEEE Transactions on Circuit Theory,1971, 18(5): 507-519.
    [3] Pershin Y V, Ventra M D. Spin memristive systems: spin memory effects in semiconductor spintronics[J].Physical Review B,2008, 78(11): 1-4.
    [4] Yang J J, Pickett M D, Li X, Ohlberg D A A, Stewart D R, Williams R S.Memristive switching mechanism for metal/oxide/metal nanodevices[J].Nature Nanotechnology,2008, 3(7): 429-433.
    [5] Wang X, Chen Y, Xi H, Li H, Dimitrov D. Spintronic memristor through-spin-torqueinduced magnetization motion[J].IEEE Electron Device Letters,2009, 30(3): 294-297.
    [6] Xia Y, Wang J. Global asymptotic and exponential stability of a dynamic-neural system with asymmetric connection weights[J].IEEE Transactions on Automatic Control,2001, 46(4): 635-638.
    [7] Hu S, Wang J. Global asymptotic stability and global exponential stability of continuous-time recurrent neural networks[J].IEEE Transactions on Automatic Control,2002, 46(5):802-807.
    [8] Cao J, Wang J. Global asymptotic stability of a general class of recurrent neural network with time-varing delays[J].IEEE Transactions on Circuits and Systems I:Fundamental Theory and Applications,2003, 50(1): 34-44.
    [9] Zhang J. Globally exponential stability of neural networks with variable delays[J].IEEE Transactions on Circuits and Systems I:Fundamental Theory and Applications,2003, 50(2): 288-291.
    [10] Zeng Z, Wang J, Liao X. Global exponential stability of a general class of recurrent neural networks with timevarying delays[J].IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, 2003, 50(10): 1353-1358.
    [11] Cao J, Wang J. Global asymptotic and robust stability of recurrent neural networks with time delays[J].IEEE Transactions on Circuits and Systems I: Regular Papers,2005, 52(2): 417-426.
    [12] Liao X, Wang J, Zeng Z. Global asymptotic stability and global exponential stability of delayed cellular neural networks[J].IEEE Transactions on Circuits and Systems II: Express Briefs,2005, 52(7): 168-173.
    [13] Zeng Z, Wang J, Liao X. Global asymptotic stability and global exponential stability of neural networks with unbounded time-varying delays[J].IEEE Transactions on Circuits and Systems II: Express Briefs,2005, 52(3): 403-409.
    [14] Cao J, Yuan K, Li H. Global asymptotical stability of recurrent neural-networks with multiple discrete delays and distributed delays[J].IEEE Transactions on Neural Networks,2006, 17(6): 1646-1651.
    [15] Zeng Z, Wang J. Improved conditions for global exponential stability of recurrent neural networks with timevarying delays[J].IEEE Transactions on Neural Networks,2006, 17(3): 623-635.
    [16] Chen W, Zheng W. Global asymptotic stability of a class of neural networks with distributed delays[J].IEEE Transactions on Circuits and Systems I: Regular Papers,2006, 53(3): 244-252.
    [17] Yu W, Cao J, Wang J. An LMI approach to delayed global asymptotic stability of the Cohen-Grossberg neural networks via nonsmooth analysis[J]. Neural Networks,2007, 20(7): 810-818.
    [18] Chen W, Zheng W. On global asymptotic stability of Cohen-Grossberg neural networks with variable delays[J].IEEE Transactions on Circuits and Systems I: Regular Papers,2008, 55(10): 3145-3159.
    [19] Shen Y, Wang J. An improved algebraic criterion for global exponential stability of recurrent neural networks with time-varying delays[J].IEEE Transactions on Neural Networks,2008, 19(3): 528-531.
    [20] Filippov A F.Differential Equations With Discontinuous Right-Hand-Sides [M]. Dordrecht: Kluwer, 1988.
    [21] Paden B E, Sastry S S. A calculus for computing Filippov’s differential inclusions with applications to the variable structure control of robot manipulators[J].IEEE Transactions on Circuits and Systems,1987, 34(1): 73-82.
    [22] Bacciotti A, Rosier L.Liapunov Functions and Stability in Control Theory [M]. 2nd ed. Communications and Control Engineering. Vol 14. London: Springer, 2005.
    [23] 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.
    [24] Berman A, Plemmons R J.Nonnegative Matrices in the Mathematical Sciences [M].New York: Academic Press, 1979.
  • 加载中
计量
  • 文章访问数:  1385
  • HTML全文浏览量:  139
  • PDF下载量:  1113
  • 被引次数: 0
出版历程
  • 收稿日期:  2013-05-07
  • 修回日期:  2013-05-09
  • 刊出日期:  2013-07-15

目录

    /

    返回文章
    返回