A winner-take-all Lotka–Volterra recurrent neural network with only one winner in each row and each column

被引：0
作者：
Bochuan Zheng
机构：
[1] China West Normal University,College of Mathematics and Information
来源：
Neural Computing and Applications | 2014年 / 24卷
关键词：
Winner-take-all; Lotka–Volterra recurrent neural networks; Convergence; Stable equilibrium point;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
A winner-take-all Lotka–Volterra recurrent neural network with N × N neurons is proposed in this paper. Sufficient conditions for existence of winner-take-all stable equilibrium points in the network are obtained. These conditions guarantee that there is one and only one winner in each row and each column at any stable equilibrium point. In addition, rigorous convergence analysis is carried out. It is proven that the proposed network model is convergent. The conditions for the winner-take-all behavior obtained in this paper provide design guidelines for network implementation and fabrication. Simulations are also presented to illustrate the theoretical findings.
引用
收藏
页码：1749 / 1757
页数：8
相关论文
共 36 条
[1]  
Urahama K(1995)-Winner-take-all circuit with IEEE Trans Neural Netw 6 775-778
[2]  
Nagao T(1999)( IEEE Trans Syst Man Cybern Part B Cybern 29 73-82
[3]  
Wang L(1997)) complexity IEEE Trans Neural Netw 8 1214-1217
[4]  
Wang L(1993)Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences IEEE Trans Circuits Syst II Analog Digital Signal Process 40 585-591
[5]  
Dempsey GL(1993)On competitive learning IEEE Trans Circuits Syst II Analog Digit Signal Process 40 184-190
[6]  
McVey ES(1996)Circuit implementation of a peak detector neural network IEEE Trans Circuits Syst II Analog Digit Signal Process 43 329-334
[7]  
Seiler G(1997)Winner-take-all cellular neural networks Neural Comput 9 77-97
[8]  
Nossek JA(1999)Improving the robustness of winner-take-all cellular neural networks Neural Netw 12 211-216
[9]  
Andrew LLH(1998)A simple neural network exhibiting selective activation of neuronal ensembles: from winner-take-all to winner-share-all Neural Netw 11 691-697
[10]  
Fukai T(2005)A subthreshold MOS circuit for the Lotka–Volterra neural network producing the winner-take-all solutions Neural Comput 17 97-114
1234