Application of Differential Evolution algorithm for automatic constructing and adapting Radial Basis Function neural networks

被引：0
|
作者：
Rymszo, Dawid [1 ]
Jankowski, Stanislaw [1 ]
机构：
[1] Warsaw Univ Technol, Inst Elect Syst, PL-00665 Warsaw, Poland
来源：
PHOTONICS APPLICATIONS IN ASTRONOMY, COMMUNICATIONS, INDUSTRY, AND HIGH-ENERGY PHYSICS EXPERIMENTS 2009 | 2009年 / 7502卷
关键词：
Differential Evolution; Radial Basis Function Network; DE-RBFN;
D O I：
10.1117/12.839615
中图分类号：
P1 [天文学];
学科分类号：
0704 ;
摘要：
The paper presents a new approach to automatic constructing and training Radial Basis Function (RBF) neural networks based on Differential Evolution (DE) algorithm. The method, called Differential Evolution-Radial Basis Function Network (DE-RBFN) is tested on approximation tasks of exemplary one- and two-dimensional Gaussian functions. Experiments are performed in Matlab environment. The results show that application of DE-RBFN enables to obtain optimal sparse network architecture by tuning the position and width of each basis function. The performance of the method is better than other related procedures applied to RBF networks
引用
收藏
页数：8
相关论文
共 50 条
  • [1] Evolutionary system for automatically constructing and adapting radial basis function networks
    Manrique, Daniel
    Rios, Juan
    Rodriguez-Paton, Alfonso
    [J]. NEUROCOMPUTING, 2006, 69 (16-18) : 2268 - 2283
  • [2] Automatic Design of Radial Basis Function Networks Through Enhanced Differential Evolution
    Bajer, Drazen
    Zoric, Bruno
    Martinovic, Goran
    [J]. HYBRID ARTIFICIAL INTELLIGENT SYSTEMS (HAIS 2015), 2015, 9121 : 244 - 256
  • [3] A new method for constructing radial basis function neural networks
    Sun, Jinyan
    Wang, Xizhao
    [J]. PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND KNOWLEDGE ENGINEERING (ISKE 2007), 2007,
  • [4] Training Radial Basis Function networks with Differential Evolution
    Yu, Bing
    He, Xingshi
    [J]. 2006 IEEE INTERNATIONAL CONFERENCE ON GRANULAR COMPUTING, 2006, : 369 - +
  • [5] Training Radial Basis Function Networks with Differential Evolution
    Yu, Bing
    He, Xingshi
    [J]. PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 11, 2006, 11 : 157 - 160
  • [6] Kernelized LARS–LASSO for constructing radial basis function neural networks
    Quan Zhou
    Shiji Song
    Cheng Wu
    Gao Huang
    [J]. Neural Computing and Applications, 2013, 23 : 1969 - 1976
  • [7] Evolutionary algorithm of radial basis function neural networks and its application in face recognition
    Li, Jianyu
    Huang, Xianglin
    Li, Rui
    Yang, Shuzhong
    Qi, Yingjian
    [J]. INTELLIGENT INFORMATION PROCESSING AND WEB MINING, PROCEEDINGS, 2006, : 65 - +
  • [8] Adapting Radial Basis Function Neural Networks for One-Class Classification
    Li, Jianwu
    Xiao, Zhanyong
    Lu, Yao
    [J]. 2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 3766 - 3770
  • [9] Approximation by Growing Radial Basis Function Networks Using the Differential-Evolution-Based Algorithm
    Liu, Junhong
    Lampinen, Jouni
    [J]. JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2005, 9 (05) : 540 - 548
  • [10] Kernelized LARS-LASSO for constructing radial basis function neural networks
    Zhou, Quan
    Song, Shiji
    Wu, Cheng
    Huang, Gao
    [J]. NEURAL COMPUTING & APPLICATIONS, 2013, 23 (7-8): : 1969 - 1976
12345