Convergence Analysis of a New MaxMin-SOMO Algorithm  

作　　者：Atlas Khan Yan-Peng Qu Zheng-Xue Li 

机构地区：[1]Department of Applied Mathematics Dalian University of Technology, Dalian 116024, China [2]School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China [3]Department of Computing and Mathematics FFCLRP, University of Sao Paulo, Ribeirao Preto, Brazil

出　　处：《International Journal of Automation and computing》2019年第4期534-542,共9页国际自动化与计算杂志（英文版）

基　　金：supported by National Natural Science Foundation of China(Nos.11171367 and 61502068);the Fundamental Research Funds for the Central Universities of China(No.3132014094);the China Postdoctoral Science Foundation(Nos.2013M541213 and 2015T80239);Fundacao da Amaro a Pesquisa do Estado de Sao Paulo(FAPESP)Brazil(No.2012/23329-5)

摘　　要：The convergence analysis of MaxMin-SOMO algorithm is presented. The SOM-based optimization (SOMO) is an optimization algorithm based on the self-organizing map (SOM) in order to find a winner in the network. Generally, through a competitive learning process, the SOMO algorithm searches for the minimum of an objective function. The MaxMin-SOMO algorithm is the generalization of SOMO with two winners for simultaneously finding two winning neurons i.e., first winner stands for minimum and second one for maximum of the objective function. In this paper, the convergence analysis of the MaxMin-SOMO is presented. More specifically, we prove that the distance between neurons decreases at each iteration and finally converge to zero. The work is verified with the experimental results.The convergence analysis of MaxMin-SOMO algorithm is presented.The SOM-based optimization(SOMO) is an optimization algorithm based on the self-organizing map(SOM) in order to find a winner in the network.Generally,through a competitive learning process,the SOMO algorithm searches for the minimum of an objective function.The MaxMin-SOMO algorithm is the generalization of SOMO with two winners for simultaneously finding two winning neurons i.e.,first winner stands for minimum and second one for maximum of the objective function.In this paper,the convergence analysis of the MaxMin-SOMO is presented.More specifically,we prove that the distance between neurons decreases at each iteration and finally converge to zero.The work is verified with the experimental results.

关 键 词：OPTIMIZATION self ORGANIZING map (SOM) SOM-based OPTIMIZATION (SOMO) ALGORITHM particle swarm OPTIMIZATION (PSO) genetic algorithms (GAs) 

分 类 号：TP[自动化与计算机技术]