Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Computer Engineering》 2006-15
Add to Favorite Get Latest Update

Stability Analysis to Hopfield Network Based on Convex Function Theory

LI Yuping1,ZHANG Suqing2,YE Shiwei2(1.Institute of Crustal Dynamics,China Earthquake Administration,Beijing 100085;2.Graduate School of Chinese Academy of Sciences,Beijing 100049)  
This paper discusses stability of discrete time Hopfield network with the sequential weight which is asymmetry or with the activation function which is non-monotonic.New energy function is imported,then it proved that the energy function of network is declined monotonously with the updating of the state using the properties of convex function,gained the sufficient condition of the network convergence in the end.To the activation function that is non-monotonic sequential function,when product of the maximum characteristic value of the network connecting weight matrix and the infimum of the derivative to the activation function of the nerve cell more than-1,the network convergences concurrently.At the same time,to the network activation function is monotonous sequential function,and the network connecting weight is asymmetry matrix,when the product of the maximum value of derivative to the nerve cell and the matrix of the two-norm to the connecting weight value is less than 1,the network convergences concurrently.
【Fund】: 中国科学院研究生院院长基金资助项目(YZJJ200206);; 国家自然科学青年项目基金资助项目(60203027)
【CateGory Index】: TP183
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【Citations】
Chinese Journal Full-text Database 4 Hits
1 YE Shi Wei 1,2 , ZHENG Hong Wei 3, WANG Wen Jie 1, MA Lin 1, and SHI Zhong Zhi 2 1(School of Information Science and Engineering, Graduate School of Chinese Acdemy of Sciences, Beijing 100039) 2(Key Laboratory of Intelligence Information Processing Institute of Computing Technology, Chinese Acdemy of Sciences, Beijing 100080) 3(Department of Mathmatics, Sichuan Normal Unversity, Chengdu 610066);Analysis for Dynamics of Discrete Time Hopfield Network[J];Journal of Computer Research and Development;2003-10
2 WANG Ling,ZHENG Dazhong (Dept.of Automation,Tsinghua University,Beijing 100084);Stability Analysis for Several Classes of Dynamical Feedback Neural Networks[J];Computing Technology and Automation;2002-01
3 YE Shi-Wei1,2+, ZHENG Hong-Wei3, WANG Wen-Jie2, MA Lin2, SHI Zhong-Zhi1 1(Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100080, China) 2(School of Information Science and Engineering , Graduate School, The Chinese Academy of Sciences, Beijing 100039, China) 3(Department of Mathematics, Sichuan Normal University, Chengdu 610066, China);Research on Stability of Discrete Time Hopfield Network[J];Journal of Software;2003-05
4 Shen Yi Liao Xiaoxin Departm entof Autom ation Control Engineering,H UST,Wuhan 430074;Global Convergence of Discrete-Time Neural Networks[J];Systems Engineering and Electronics;1999-11
【Secondary Citations】
Chinese Journal Full-text Database 1 Hits
1 Wang Ling, Zheng Dazhong (Tsinghua University);Study on TSP and Optimization Based on Hopfield Neural Network[J];CONTROL AND DECISION;1999-06
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved