Training radial basis function networks with particle swarms

被引：0
|
作者：
Liu, Y [1 ]
Zheng, Q
Shi, ZW
Chen, JY
机构：
[1] Xi An Jiao Tong Univ, Dept Comp Sci, Xian 710049, Peoples R China
[2] Tsinghua Univ, Sch Software, Beijing 100084, Peoples R China
来源：
ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1 | 2004年 / 3173卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, Particle Swarm Optimization (PSO) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, PSO achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.
引用
收藏
页码：317 / 322
页数：6
相关论文
共 50 条
  • [41] Multistage Newton’s Approach for Training Radial Basis Function Neural Networks
    Tyagi K.
    Rane C.
    Irie B.
    Manry M.
    [J]. SN Computer Science, 2021, 2 (5)
  • [42] Lazy training of radial basis neural networks
    Valls, Jose M.
    Galvan, Ines M.
    Isasi, Pedro
    [J]. ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 1, 2006, 4131 : 198 - 207
  • [43] Radar target classification based on radial basis function and modified radial basis function networks
    Liu, GS
    Wang, YH
    Yang, CL
    Zhou, DQ
    [J]. ICR '96 - 1996 CIE INTERNATIONAL CONFERENCE OF RADAR, PROCEEDINGS, 1996, : 208 - 211
  • [44] Function emulation using radial basis function networks
    Chakravarthy, SV
    Ghosh, J
    [J]. NEURAL NETWORKS, 1997, 10 (03) : 459 - 478
  • [45] Training radial basis function networks for process identification with an emphasis on the Bayesian evidence approach
    Kershenbaum, LS
    Magni, AR
    [J]. APPLICATION OF NEURAL NETWORKS AND OTHER LEARNING TECHNOLOGIES IN PROCESS ENGINEERING, 2001, : 77 - 98
  • [46] Fast and Efficient Second-Order Method for Training Radial Basis Function Networks
    Xie, Tiantian
    Yu, Hao
    Hewlett, Joel
    Rozycki, Pawel
    Wilamowski, Bogdan
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (04) : 609 - 619
  • [47] Adaptive training of Radial Basis Function Networks based on cooperative evolution and evolutionary programming
    Topchy, AP
    Lebedko, OA
    Miagkikh, VV
    Kasabov, NK
    [J]. PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 253 - 258
  • [48] ORTHOGONAL LEAST-SQUARES ALGORITHM FOR TRAINING MULTIOUTPUT RADIAL BASIS FUNCTION NETWORKS
    CHEN, S
    GRANT, PM
    COWAN, CFN
    [J]. IEE PROCEEDINGS-F RADAR AND SIGNAL PROCESSING, 1992, 139 (06) : 378 - 384
  • [49] Comparative study between radial basis probabilistic neural networks and radial basis function neural networks
    Zhao, WB
    Huang, DS
    Guo, L
    [J]. INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING, 2003, 2690 : 389 - 396
  • [50] Generalization Performance of Radial Basis Function Networks
    Lei, Yunwen
    Ding, Lixin
    Zhang, Wensheng
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (03) : 551 - 564
12345