Convergence Analysis of a New MaxMin-SOMO Algorithm

被引：0
|
作者：
Khan, Atlas [1 ,3 ]
Qu, Yan-Peng [2 ]
Li, Zheng-Xue [1 ]
机构：
[1] Dalian Univ Technol, Dept Appl Math, Dalian 116024, Peoples R China
[2] Dalian Maritime Univ, Sch Informat Sci & Technol, Dalian 116026, Peoples R China
[3] Univ Sao Paulo, Dept Comp & Math FFCLRP, Ribeirao Preto, Brazil
来源：
INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING | 2019年 / 16卷 / 04期
基金：
中国博士后科学基金; 中国国家自然科学基金; 巴西圣保罗研究基金会;
关键词：
Optimization; self organizing map (SOM); SOM-based optimization (SOMO) algorithm; particle swarm optimization (PSO); genetic algorithms (GAs); SELF-ORGANIZING MAP;
D O I：
10.1007/s11633-016-0996-0
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
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.
引用
收藏
页码：534 / 542
页数：9
相关论文
共 50 条
  • [41] SOMO-m Optimization Algorithm with Multiple Winners
    Wu, Wei
    Khan, Atlas
    DISCRETE DYNAMICS IN NATURE AND SOCIETY, 2012, 2012
  • [42] Global Convergence Analysis of a New Nonmonotone BFGS Algorithm on Convex Objective Functions
    Jiye Han
    Guanghui Liu
    Computational Optimization and Applications, 1997, 7 : 277 - 289
  • [43] CONVERGENCE ANALYSIS OF A NEW ITERATIVE ALGORITHM FOR SOLVING SPLIT VARIATIONAL INCLUSION PROBLEMS
    Tang, Yan
    JOURNAL OF INDUSTRIAL AND MANAGEMENT OPTIMIZATION, 2020, 16 (02) : 945 - 964
  • [44] Global convergence analysis of a new nonmonotone BFGS algorithm on convex objective functions
    Academia Sinica, Beijing, China
    Comput Optim Appl, 3 (277-289):
  • [45] A new multi-modal immune algorithm and its complete convergence analysis
    Yang, Kongyu
    Sun, Zhiheng
    Liang, Yan
    ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 3, PROCEEDINGS, 2007, : 813 - +
  • [46] Convergence Analysis of the New Hybrid Genetic Algorithm for the Job Shop Scheduling Problem
    Nguyen Huu Mui
    Vu Dinh Hoa
    Luc Tri Tuyen
    2012 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT), 2012, : 7 - 12
  • [47] Global convergence analysis of a new nonmonotone BFGS algorithm on convex objective functions
    Han, JY
    Liu, GH
    COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 1997, 7 (03) : 277 - 289
  • [48] CONVERGENCE ANALYSIS OF A NEW RELAXED ALGORITHM WITH INERTIAL FOR SOLVING SPLIT FEASIBILITY PROBLEMS
    Ogbuisi, Ferdinard U.
    Shehu, Yekini
    Yao, Jen-chih
    FIXED POINT THEORY, 2024, 25 (01): : 249 - 270
  • [49] Convergence analysis of butterfly optimization algorithm
    Chakraborty, Prasanjit
    Sharma, Sushmita
    Saha, Apu Kumar
    SOFT COMPUTING, 2023, 27 (11) : 7245 - 7257
  • [50] Convergence analysis of parallel alternating algorithm
    Wang, Guangbin
    Tan, Fuping
    ISISE 2008: INTERNATIONAL SYMPOSIUM ON INFORMATION SCIENCE AND ENGINEERING, VOL 1, 2008, : 76 - +
12345