NOVEL FAST TRAINING ALGORITHM FOR MULTILAYER FEEDFORWARD NEURAL NETWORK

被引:9
|
作者
PARK, DJ
JUN, BE
KIM, JH
机构
[1] Department of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Taejon 305-701, 373-1 Kusong-dong, Yusung-gu
关键词
NEURAL NETWORKS; ALGORITHMS;
D O I
10.1049/el:19920343
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A new fast learning algorithm for a multilayer feedforward neural network is presented. The new algorithm, based on an innovative variable step size and gradient averaging, has excellent properties to overcome major drawbacks of the backpropagation algorithm and shows high convergence speed. The improved performance of the new algorithm in comparison with other algorithms is verified via computer simulations.
引用
收藏
页码:543 / 545
页数:3
相关论文
共 50 条
  • [21] A novel link structure and learning algorithm of feedforward neural network
    Wu, Y
    2004 7TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS 1-3, 2004, : 1534 - 1537
  • [22] An incremental algorithm for parallel training of the size and the weights in a feedforward neural network
    Hlavácková-Schindler, K
    Fischer, MM
    NEURAL PROCESSING LETTERS, 2000, 11 (02) : 131 - 138
  • [23] An Incremental Algorithm for Parallel Training of the Size and the Weights in a Feedforward Neural Network
    Kateřina Hlaváčková-Schindler
    Kateřina Hlaváčková-Schindler
    Manfred M. Fischer
    Neural Processing Letters, 2000, 11 : 131 - 138
  • [24] THE SYSTEMATIC TRAJECTORY SEARCH ALGORITHM FOR THE GENERALIZED FEEDFORWARD NEURAL NETWORK TRAINING
    Chen, Wen-Ching
    Tseng, Lin-Yu
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2011, 7 (5A): : 2457 - 2471
  • [25] An efficient recursive total least squares algorithm for training multilayer feedforward neural networks
    Choi, NJ
    Lim, JS
    Sung, KM
    ADVANCES IN NEURAL NETWORKS - ISNN 2005, PT 1, PROCEEDINGS, 2005, 3496 : 558 - 565
  • [26] A novel multicriteria optimization algorithm for the structure determination of multilayer feedforward neural networks
    Kottathra, K
    Attikiouzel, Y
    JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 1996, 19 (02) : 135 - 147
  • [27] A fast learning strategy for multilayer feedforward neural networks
    Chen, Huawei
    Zhong, Hualan
    Yuan, Haiying
    Jin, Fan
    WCICA 2006: SIXTH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-12, CONFERENCE PROCEEDINGS, 2006, : 3019 - +
  • [28] A fast multilayer neural-network training algorithm based on the layer-by-layer optimizing procedures
    Wang, GJ
    Chen, CC
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (03): : 768 - 775
  • [29] A fast and numerically robust neural network training algorithm
    Zhang, Youmin
    ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING - ICAISC 2006, PROCEEDINGS, 2006, 4029 : 160 - 169
  • [30] A fast compositive training algorithm of forward neural network
    Sun, Baiqing
    Wang, Xiaohong
    Wang, Xuefeng
    Pan, Qishu
    PROCEEDINGS OF THE 2006 IEEE INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL, 2006, : 183 - 188