时间标度上时滞脉冲复值神经网络的全局稳定性

闫欢; 宋乾坤; 赵振江

doi:10.3879/j.issn.1000-0887.2015.11.007

时间标度上时滞脉冲复值神经网络的全局稳定性

doi: 10.3879/j.issn.1000-0887.2015.11.007

¹重庆交通大学信息科学与工程学院,重庆 400074;²重庆交通大学数学系,重庆 400074;³湖州师范学院数学系, 浙江湖州 313000

基金项目: 国家自然科学基金（61273021; 61473332）; 重庆市研究生科研创新项目(CYS14163)

详细信息

作者简介:
闫欢(1991—)，女，重庆万州人，硕士生(E-mail: huanyancquc@163.com);宋乾坤(1963—)，男，四川岳池人，教授，博士(通讯作者. E-mail: qiankunsong@163.com);赵振江（1961—），男，新疆喀什人，教授，硕士(E-mail: zhaozjcn@163.com).

中图分类号: O175.13
计量
- 文章访问数: 1783
- HTML全文浏览量: 171
- PDF下载量: 819
- 被引次数: 0
出版历程
- 收稿日期: 2015-06-16
- 修回日期: 2015-07-21
- 刊出日期: 2015-11-15

Global Stability of Impulsive Complex-Valued Neural Networks With Time Delay on Time Scales

¹School of Information Science and Engineering, Chongqing Jiaotong University,Chongqing 400074, P.R.China;²Department of Mathematics, Chongqing Jiaotong University,Chongqing 400074, P.R.China;³Department of Mathematics, Huzhou University,Huzhou, Zhejiang 313000, P.R.China

Funds: The National Natural Science Foundation of China(（61273021; 61473332)

摘要

摘要: 研究了时间标度上具有时滞和脉冲影响的复值神经网络的全局稳定性问题.利用时间标度上的微积分理论，将连续时间型复值神经网络和离散时间型复值神经网络统一在同一个框架下进行研究.在不要求激励函数有界的条件下，运用同胚映射原理，建立了确保时滞复值神经网络平衡点存在性和唯一性的判定条件.通过构造合适的Lyapunov-Krasovskii泛函，并使用自由权矩阵方法和矩阵不等式技巧，获得了时间标度上具有时滞和脉冲影响的复值神经网络平衡点全局稳定性的充分条件.给出的判据是由复值线性矩阵表示的，易于MATLAB软件的YALMIP Toolbox实现.数值仿真实例验证了获得结果的有效性.
- 复值神经网络 /
- 时间标度 /
- 时滞 /
- 脉冲 /
- 复值线性矩阵不等式 /
- 全局稳定性
Abstract: The global stability of impulsive complex-valued neural networks with time delay on time scales was investigated. Based on the time scale calculus theory, both the continuous-time and discrete-time neural networks were described under the same framework. For the considered complex-valued neural networks, the activation functions need not be bounded. According to the homeomorphism mapping principle in the complex domain, a sufficient condition for the existence and uniqueness of the equilibrium point of the addressed complex-valued neural networks was proposed in complex-valued linear matrix inequality (LMI). Through the construction of appropriate Lyapunov-Krasovskii functionals, and with the free weighting matrix method and matrix inequality technique, a delay-dependent criterion for checking the global stability of the complex-valued neural networks was established in the complex-valued LMIs. Finally, a simulation example shows the effectiveness of the obtained results.
- complex-valued neural network /
- time scale /
- time delay /
- impulsive /
- linear matrix inequality /
- global stability

HTML全文

参考文献(22)

[1]	廖晓昕. 细胞神经网络的数学理论(Ⅰ)[J]. 中国科学(A辑), 1994,24(9): 902-910.(LIAO Xiao-xin. The mathematical theory of cellular neural networks I[J]. Science in China(Series A),1994,24(9): 902-910.(in Chinese))
[2]	廖晓昕. 细胞神经网络的数学理论(Ⅱ)[J]. 中国科学(A辑), 1994,24(10): 1037-1046.(LIAO Xiao-xin. The mathematical theory of cellular neural networks II[J]. Science in China(Series A),1994,24(10): 1037-1046.(in Chinese))
[3]	Arik S. Stability analysis of delayed neural networks[J]. IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications,2000,47(7): 1089-1092.
[4]	CAO Jin-de. Exponential stability and periodic solutions of delayed cellular neural networks[J]. Science China Technological,2000,43(3): 328-336.
[5]	SONG Qian-kun. Exponential stability of recurrent neural networks with both time-varying delays and general activation functions via LMI approach[J]. Neurocomputing,2008,71(13/15): 2823-2830.
[6]	GUAN Zhi-hong, CHEN Guan-rong. On delayed impulsive Hopfield neural networks[J]. Neural Networks,1999,12(2): 273-280.
[7]	SONG Qian-kun, CAO Jin-de. Impulsive effects on stability of fuzzy Cohen-Grossberg neural networks with time-varying delays[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics,2007,37(3): 733-741.
[8]	Tojtovska B, Jankovic S. General decay stability analysis of impulsive neural networks with mixed time delays[J]. Neurocomputing,2014,142: 438-446.
[9]	Hirose A. Complex-Valued Neural Networks: Theories and Applications [M]. Singapore: World Scientific, 2003.
[10]	Rao V S H, Murthy G R. Global dynamics of a class of complex valued neural networks[J]. International Journal of Neural Systems,2008,18(2): 165-171.
[11]	ZHOU Wei, Zurada J M. Discrete-time recurrent neural networks with complex-valued linear threshold neurons[J]. IEEE Transactions on Circuits and Systems II: Express Briefs,2009,56(8): 669-673.
[12]	DUAN Cheng-jun, SONG Qian-kun. Boundedness and stability for discrete-time delayed neural network with complex-valued linear threshold neurons[J]. Discrete Dynamics in Nature and Society,2010,2010, article ID 368379.
[13]	Jankowski S, Lozowski A, Zurada J. Complex-valued multistate neural associative memory[J]. IEEE Transactions on Neural Networks,1996,7(6): 1491-1496.
[14]	Lee D. Relaxation of the stability condition of the complex-valued neural networks[J]. IEEE Transactions on Neural Networks,2001,12(5): 1260-1262.
[15]	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): 853-865.
[16]	ZHOU Bo, SONG Qian-kun. Boundedness and complete stability of complex-valued neural networks with time delay[J]. IEEE Transactions on Neural Networks and Learning Systems,2013, 24(8): 1227-1238.
[17]	ZHANG Zi-ye, LIN Chong, CHEN Bing. Global stability criterion for delayed complex-valued recurrent neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems,2014,25(9): 1704-1708.
[18]	FANG Tao, SUN Ji-tao. Stability of complex-valued recurrent neural networks with time-delays[J]. IEEE Transactions on Neural Networks and Learning Systems,2014,25(9): 1709-1713.
[19]	Hilger S. Analysis on measure chains—a unified approach to continuous and discrete calculus[J]. Results in Mathematics,1990,18(1): 18-56.
[20]	Bohner M, Sree Hari Rao V, Sanyal S. Global stability of complex-valued neural networks on time scales[J]. Differential Equations and Dynamical Systems,2011,19(1/2): 3-11.
[21]	CHEN Xiao-feng, SONG Qian-kun. Global stability of complex-valued neural networks with both leakage time delay and discrete time delay on time scales[J]. Neurocomputing,2013,121: 254-264.
[22]	Rakkiyappan R, Velmurugan G, LI Xiao-di. Complete stability analysis of complex-valued neural networks with time delays and impulses[J]. Neural Processing Letters,2015,41(3): 435-468.

施引文献

资源附件(0)

访问统计

计量

文章访问数: 1783
HTML全文浏览量: 171
PDF下载量: 819
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

时间标度上时滞脉冲复值神经网络的全局稳定性

doi: 10.3879/j.issn.1000-0887.2015.11.007

作者简介:
闫欢(1991—)，女，重庆万州人，硕士生(E-mail: huanyancquc@163.com);宋乾坤(1963—)，男，四川岳池人，教授，博士(通讯作者. E-mail: qiankunsong@163.com);赵振江（1961—），男，新疆喀什人，教授，硕士(E-mail: zhaozjcn@163.com).

计量

Global Stability of Impulsive Complex-Valued Neural Networks With Time Delay on Time Scales

计量

目录

留言板

时间标度上时滞脉冲复值神经网络的全局稳定性

doi: 10.3879/j.issn.1000-0887.2015.11.007

作者简介: 闫欢(1991—)，女，重庆万州人，硕士生(E-mail: huanyancquc@163.com);宋乾坤(1963—)，男，四川岳池人，教授，博士(通讯作者. E-mail: qiankunsong@163.com);赵振江（1961—），男，新疆喀什人，教授，硕士(E-mail: zhaozjcn@163.com).

计量

出版历程

Global Stability of Impulsive Complex-Valued Neural Networks With Time Delay on Time Scales

计量

出版历程

目录

作者简介:
闫欢(1991—)，女，重庆万州人，硕士生(E-mail: huanyancquc@163.com);宋乾坤(1963—)，男，四川岳池人，教授，博士(通讯作者. E-mail: qiankunsong@163.com);赵振江（1961—），男，新疆喀什人，教授，硕士(E-mail: zhaozjcn@163.com).