A genetic algorithm based variable structure Neural Network

被引：4
|
作者：
Ling, SH [1 ]
Lam, HK [1 ]
Leung, FHF [1 ]
Lee, YS [1 ]
机构：
[1] Hong Kong Polytech Univ, Dept Elect & Informat Engn, Ctr Multimedia Signal Proc, Kowloon, Hong Kong, Peoples R China
来源：
IECON'03: THE 29TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1 - 3, PROCEEDINGS | 2003年
关键词：
genetic algorithm; neural network; hand-written pattern recognition;
D O I：
10.1109/IECON.2003.1280020
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presents a neural network model with a variable structure, which is trained by genetic algorithm (GA). The proposed neural network consists of a Neural Network with a Node-to-Node Relationship ((NR)-R-4) and a Network Switch Controller (NSC). In the (NR)-R-4, a modified neuron model with two activation functions in the hidden layer, and switches in its links are introduced. The NSC controls the switches in the (NR)-R-4. The proposed neural network can model different input patterns with variable network structures. The proposed neural network provides better result and learning ability than traditional feed forward neural networks. Two application examples on XOR problem and hand-written pattern recognition are given to illustrate the merits of the proposed network.
引用
收藏
页码：436 / 441
页数：6
相关论文
共 50 条
  • [21] The research on Optimization neural network structure parallel genetic algorithm
    Yu, Mingyan
    Yan, Ying
    Liu, Haiyuan
    Zhi, HeCai
    ADVANCES IN MANUFACTURING TECHNOLOGY, PTS 1-4, 2012, 220-223 : 2564 - +
  • [22] A solution representation of genetic algorithm for neural network weights and structure
    Jaddi, Najmeh Sadat
    Abdullah, Salwani
    Hamdan, Abdul Razak
    INFORMATION PROCESSING LETTERS, 2016, 116 (01) : 22 - 25
  • [23] Genetic Algorithm to the Formation of the Optimal Structure of Fuzzy Neural Network
    Filatova, E. S.
    Filatov, D. M.
    Stotckaia, A. D.
    2015 XVIII International Conference on Soft Computing and Measurements (SCM), 2015, : 147 - 149
  • [24] Use of genetic algorithm to design optimal neural network structure
    Öztürk, N
    ENGINEERING COMPUTATIONS, 2003, 20 (7-8) : 979 - 997
  • [25] Hybrid Intelligent Algorithm of RBF Neural Network with Variable Length Structure
    She Yuanguo
    INFORMATION-AN INTERNATIONAL INTERDISCIPLINARY JOURNAL, 2012, 15 (06): : 2571 - 2577
  • [26] Genetic algorithm and neural network
    Stastny, Jiri
    Skorpil, Vladislav
    PROCEEDINGS OF THE 7TH WSEAS INTERNATIONAL CONFERENCE ON APPLIED INFORMATICS AND COMMUNICATIONS, 2007, : 347 - 351
  • [27] A genetic algorithm for tuning variable orderings in Bayesian network structure learning
    Guo, HP
    Perry, BB
    Stilson, JA
    Hsu, WH
    EIGHTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-02)/FOURTEENTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-02), PROCEEDINGS, 2002, : 951 - 952
  • [28] The analysis of convergence of hybrid algorithm based on neural network and genetic algorithm
    Pan, MQ
    He, GP
    PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON NEURAL NETWORKS AND BRAIN, VOLS 1-3, 2005, : 232 - 235
  • [29] Study on a neural network optimization algorithm based on improved genetic algorithm
    Liu, Haoran (liu.haoran@ysu.edu.cn), 1600, Science Press (37):
  • [30] Dynamic structure-based neural network determination using orthogonal genetic algorithm with quantization
    Xing, Liling
    Zhao, Wentao
    BIO-INSPIRED COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2007, 4688 : 162 - +
12345