Global Stability Analysis of Cohen-Grossberg Neural Networks with Unbounded Time Delays
-
摘要: 为将神经网络应用于最优化问题的求解,对具有无穷时滞的Cohen-Grossberg神经网络平衡点的存在性、唯一性和全局渐近稳定性进行了探讨.在不假设激活函数有界性、单调性和可微性的情况下,得到了系统平衡点的存在性条件.利用向量Liapunov函数法,构造适当的含有无穷时滞的微分-积分不等式,并分析了微分-积分不等式的稳定性,得到了Cohen-Grossberg神经网络系统全局渐近稳定性的判据.通过判断由神经网络的权系数、自反馈函数以及激励函数构造的矩阵是否为M-矩阵,即可得到Cohen-Grossberg神经网络系统的全局渐近稳定性.最后给出了一个算例,以说明该判据的正确性.Abstract: In order to apply the neural networks to optimization problems,the conditions ensuring the existence,uniqueness and global asymptotical stability of the equilibrium point of Cohen-Grossberg neural networks(CGNN)with unbounded time delays were investigated.Without assuming the boundedness,monotone and differentiability of the activation functions,the existence condition of the equilibrium point of CGNN was obtained.Using the vector Liapunov function method,the intero-differential inequalities with unbounded time delays were constructed,and the stability of the intero-differential inequalities were analyzed to obtain the criteria for the global asymptotical stability of the equilibrium point.Based on the criteria,the global asymptotic stability of CGNN can be get by judging whether the matrix constructed by the weighed coefficients,self-feedback functions and activation functions of CGNN is an M-matrix.Finally,an example was given to testify the validity of the criteria.
-
Key words:
- neural network /
- time delay /
- stability
-
COHEN M A,GROSSBERG S.Absolute stability and global pattern formation and parallel memory storage by competitive neural networks[J].IEEE Transactions on Systems,Man and Cybernetics Society,1983,13(5):815-825.[2] 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,1995,42(7):354-366.[3] ARIK S,TAVANOGLU V.On the global asymptotic stability of delayed cellular neural networks[J].IEEE Transactions on Circuits and Systems-I,2000,47(4):571-574.[4] GOPALSAMY K,HE X.Stability in asymmetric Hopfield nets with transmission delays[J].Physica D,1994,76(4):344-358.[5] SREE H R V,PHANEENDRA B R M.Global dynamics of bidirectional associative memory neural networks involving transmission delays and dead zones[J].Neural Networks,1999,12(3)455-465.[6] ZHANG Jiye,SUDA Y,IWASA T.Absolutely exponential stability of a class of neural networks with unbounded delay[J].Neural Networks,2004,17(3):391-397.[7] ZHANG Jiye.Globally exponential stability of neural networks with variable delays[J].IEEE Transactions on Circuits and Systems-I,2003,50(2):288-291.[8] ZHANG Jiye,SUDA Y,KOMINE H.Global exponential stability of cohen-grossberg neural networks with variable delays[J].Physics Letter A,2005,338(1):44-50.[9] ZHANG Jiye.Global stability analysis in cellular neural networks with unbounded time delays[J].Applied Mathematics and Mechanics-English Edition,2004,25 (6):686-693.[10] 舒仲周,张继业,曹登庆.运动稳定性[M].北京:中国铁道出版社,2001:148-167.[11] 张克跃,任殿波,张继业.分布时滞动态神经网络的全局指数稳定性[J].西南交通大学学报,2008,43(1):57-61.ZHANG Keyue,REN Dianbo,ZHANG Jiye.Global exponential stability of dynamic neural networks with distributed delays[J].Journal of Southwest Jiaotong University,2008,43(1):57-61.[12] SILJIAK D D.Large-scale dynamic systems-stability and structure[M].New York:Elsevier North-Holland Inc.,1978:165-171.[13] 张继业,杨翊仁,曾京.无限维关联系统的弦稳定性[J].应用数学和力学,2000,21(7):715-720. ZHANG Jiye,YANG Yiren,ZENG Jing.String stability of infinite interconnected system[J].Applied Mathematics and Mechanics,2000,21(7):715-720.[14] HALE J K,LUNEL S M V.Introduction to functional differential equations[M].New York:Springer-Verlag,1993:130-150.
点击查看大图
计量
- 文章访问数: 2006
- HTML全文浏览量: 69
- PDF下载量: 459
- 被引次数: 0