Absolute Exponential Stability of Generalized Hopfield Neural Networks
-
摘要: 研究了一类广义神经网络系统平衡点的存在性、唯一性和绝对指数稳定性.这类神经网络包含Hopfield神经网络和细胞型神经网络,不要求激活函数可微和有界.应用拓扑理论,得到了广义Hopfield神经网络平衡点的存在性和唯一性的充分必要条件;利用矩阵的性质,通过构造Lurie型Liapunov函数,得到了广义Hopfield神经网络绝对指数稳定的充分条件以及几类特殊神经网络绝对指数稳定的充分必要条件.Abstract: The existence and uniqueness of the equilibrium point of a class of generalized Hopfield neural networks(GHNN),altogether with its absolute exponential stability,were investigated.GHNN includes Hopfield neural networks and cellular neural networks,and it is not necessary for its activation functions to be differential and bounded functions.By applying the topology theory,the necessary and sufficient condition for the existence and uniqueness of the equilibrium point of GHNN was obtained.Based on matrix properties,the sufficient conditions for the absolute exponential stability of GHNN were given by constructing Lurie-type Liapunov functions.In some special cases,the necessary and sufficient conditions of the absolute exponential stability of neural networks were determined.
-
HOPFIED J J.Neurons with graded response have collective computational properties like those of two state neurons[J].Proc.Natl.Acad.Sci.,1984,81(5):3 088-3 092.[2] MICHEL A N,FARRELL J A,POROD W.Qualitative analysis of neural networks[J].IEEE Transactions on Circuits and Systems,1989,36(2):229-243.[3] FROTI 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.[4] FROTI M,MANETTI S,MARINI M.Necessary and sufficient condition for absolute stability of neural networks[J].IEEE Transactions on Circuits and Systems-Ⅰ:Fundamental Theory and Applications,1994,41 (7):491-494.[5] FROTI M.A note on neural networks with multiple equilibrium points[J].IEEE Transaction on Circuits and Systems-Ⅰ:Fundamental Theory and Applications,1996,43 (6):487-491.[6] LIANG X,WU L.New sufficient conditions for absolute stability of neural networks[J].IEEE Transactions on Circuits and Systems-Ⅰ:Fundamental Theory and Applications,1998,45(5):584-586.[7] 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,1998,12:455-465.[8] VAN D D P,ZOU X.Global attractivity in delayed Hopfield neural networks models[J].SIAM J.Appl.Math.,1998,58(6):1 878-1 890.[9] 谭晓惠,张继业,杨翊仁.Hopfield神经网络的全局指数稳定性[J].西南交通大学学报,2005,40(3):338-342.TAN Xiaohui,ZHANG Jiye,YANG Yiren.Global exponential stability of Hopfield neural networks[J].Journal of Southwest Jiaotong University,2005,40 (3):338-342.[10] 廖晓昕.Hopfield型神经网络的稳定性[J].中国科学(A),1993,23(10):1 025-1 035.LIAO Xiaoxin.Stability of Hopfield-type neutral networks[J].Sciencein China(Series A),1993,23(10):1 025-1 035.[11] 梁学斌,吴立德.Hopfield型神经网络的全局指数稳定性及其应用[J].中国科学(A),1995,25(5):523-532.LIANG Xuebin,WU Lide.Global exponential stability of Hopfield-type neutral networks and its applications[J].Science in China (Series A),1995,25(5):523-532.[12] ZHANG Y,HENG P A,Fu W C.Estimate of exponential convergence rate and exponential stability for neural networks[J].IEEE Transactions on Neural Networks,1999,10(6):1 487-1 493.[13] GUAN Z,CHEN G.On delayed impulsive Hopfield neural networks[J].Neural Networks,1999,12:273-280.[14] ZHANG J Y,JINX S.Global stability analysis in delayed Hopfield neural networks models[J].Neural Networks,2000,13(7):745-753.[15] ZHANG J Y.Absolute stability analysis in cellular neural networks with variable delays and unbounded delay[J].Computers and Mathematics with Applications,2004,47 (2-3):183-194.[16] CHUA L O,YANG L.Cellular neural networks[J].IEEE Transactions on Circuits and Systems,1988,35 (10):1 257-1 272.[17] 舒仲周,张继业,曹登庆.运动稳定性[M].北京:中国铁道出版社,2001:148-166.
点击查看大图
计量
- 文章访问数: 1600
- HTML全文浏览量: 70
- PDF下载量: 293
- 被引次数: 0