An improved training algorithm for feedforward neural network learning based on terminal attractors

被引：0
|
作者：
Xinghuo Yu
Bin Wang
Batsukh Batbayar
Liuping Wang
Zhihong Man
机构：
[1] RMIT University,Platform Technologies Research Institute
[2] Southeast University,School of Automation
[3] RMIT University,School of Electrical and Computer Engineering
[4] National University of Mongolia,School of Information Technology
[5] Swinburne University of Technology,Faculty of Engineering and Industrial Sciences
来源：
Journal of Global Optimization | 2011年 / 51卷
关键词：
Feedforward neural network; Terminal attractor; Back-propagation; Training; Optimization;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper, an improved training algorithm based on the terminal attractor concept for feedforward neural network learning is proposed. A condition to avoid the singularity problem is proposed. The effectiveness of the proposed algorithm is evaluated by various simulation results for a function approximation problem and a stock market index prediction problem. It is shown that the terminal attractor based training algorithm performs consistently in comparison with other existing training algorithms.
引用
收藏
页码：271 / 284
页数：13
相关论文
共 50 条
  • [1] An improved training algorithm for feedforward neural network learning based on terminal attractors
    Yu, Xinghuo
    Wang, Bin
    Batbayar, Batsukh
    Wang, Liuping
    Man, Zhihong
    [J]. JOURNAL OF GLOBAL OPTIMIZATION, 2011, 51 (02) : 271 - 284
  • [2] An Improved Levenberg-Marquardt Learning Algorithm for Neural Networks Based on Terminal Attractors
    Batbayar, Batsukh
    Yu, Xinghuo
    [J]. 2008 2ND INTERNATIONAL SYMPOSIUM ON SYSTEMS AND CONTROL IN AEROSPACE AND ASTRONAUTICS, VOLS 1 AND 2, 2008, : 333 - 336
  • [3] An improved feedforward fuzzy neural network and its learning algorithm
    Liu, PY
    [J]. JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING, 2004, 10 (03) : 203 - 223
  • [4] A new feedforward neural network structural learning algorithm - Augmentation by training with residuals
    Li, CJ
    Kim, T
    [J]. JOURNAL OF DYNAMIC SYSTEMS MEASUREMENT AND CONTROL-TRANSACTIONS OF THE ASME, 1995, 117 (03): : 411 - 415
  • [5] Efficient learning algorithm for feedforward neural network
    Du, Zhengchun
    Liu, Yutian
    Xia, Daozhi
    [J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 1995, 23 (08): : 57 - 61
  • [6] An efficient learning algorithm for feedforward neural network
    Tan, SB
    Gu, J
    [J]. ADVANCES IN ARTIFICIAL INTELLIGENCE - IBERAMIA 2004, 2004, 3315 : 767 - 777
  • [7] Training algorithm of one feedforward wavelet neural network
    Zhao, G
    Zhao, J
    Chen, W
    Li, JP
    [J]. WAVELET ANALYSIS AND ITS APPLICATIONS, AND ACTIVE MEDIA TECHNOLOGY, VOLS 1 AND 2, 2004, : 135 - 142
  • [8] A fast learning algorithm for training feedforward neural networks
    Goel, Ashok Kumar
    Saxena, Suresh C.
    Bhanot, Surekha
    [J]. INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 2006, 37 (10) : 709 - 722
  • [9] An improved genetic algorithm for training layered feedforward neural networks
    Liu Ping
    Cheng Yi-yu
    [J]. Journal of Zhejiang University-SCIENCE A, 2000, 1 (3): : 322 - 326
  • [10] Training feedforward neural networks: An algorithm giving improved generalization
    Lee, CW
    [J]. NEURAL NETWORKS, 1997, 10 (01) : 61 - 68
12345