A fast hybrid algorithm of global optimization for feedforward neural networks

被引：0
|
作者：
Jiang, MH [1 ]
Zhang, B
Zhu, XY
Jinag, MY
机构：
[1] Tsing Hua Univ, Dept Chinese Language, Lab Computat Linguist, Beijing 100084, Peoples R China
[2] Tsing Hua Univ, Dept Comp, State Key Lab Intelligent Tech & Syst, Beijing 100084, Peoples R China
[3] Shandong Univ, Dept Elect Engn, Jinan 250100, Peoples R China
来源：
CHINESE JOURNAL OF ELECTRONICS | 2001年 / 10卷 / 02期
关键词：
the conjugate gradient algorithm; global convergence; backpropagation;
D O I：
暂无
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：
This paper presents the hybrid algorithm of global optimization of dynamic learning rate for multilayer feedforward neural networks (MLFNN), The effect of inexact line search on conjugacy was studied, based on which a generalized conjugate gradient method was proposed, showing global convergence for error backpagation of MLFNN, It overcomes the drawback of conventional BP and Polak-Ribieve conjugate gradient algorithms that maybe plunge into local minima. The hybrid algorithm's recognition rate is higher than that of Polak-Ribieve algorithm and convergence BP for test data, its training time is less than that of Fletcher-Reeves algorithm and far less than that of convergence BP, and it has a less complicated and stronger robustness to real speech data.
引用
收藏
页码：214 / 218
页数：5
相关论文
共 50 条
  • [1] A fast hybrid algorithm of global optimization for feedforward neural networks
    Jiang, MH
    Zhu, XY
    Yuan, BZ
    Tang, XF
    Lin, BQ
    Ruan, QQ
    Jiang, MY
    [J]. 2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, : 1609 - 1612
  • [2] A novel global hybrid algorithm for feedforward neural networks
    Li, Hongru
    Li, Hailong
    Du, Yina
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 3, PROCEEDINGS, 2007, 4493 : 9 - +
  • [3] A global optimization algorithm for training feedforward neural networks
    Huanqin Li
    [J]. DYNAMICS OF CONTINUOUS DISCRETE AND IMPULSIVE SYSTEMS-SERIES B-APPLICATIONS & ALGORITHMS, 2006, 13 : 846 - 849
  • [4] A hybrid algorithm for weight and connectivity optimization in feedforward neural networks
    Pettersson, F
    Saxén, H
    [J]. ARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS, PROCEEDINGS, 2003, : 47 - 52
  • [5] Global Optimization of Feedforward Neural Networks
    LIANG Xun XIA Shaowei Department of Automation
    [J]. Journal of Systems Science and Systems Engineering, 1993, (03) : 273 - 280
  • [6] A hybrid training algorithm for feedforward neural networks
    Ben Nasr, Mounir
    Chtourou, Mohamed
    [J]. NEURAL PROCESSING LETTERS, 2006, 24 (02) : 107 - 117
  • [7] A Hybrid Training Algorithm for Feedforward Neural Networks
    Mounir Ben Nasr
    Mohamed Chtourou
    [J]. Neural Processing Letters, 2006, 24 : 107 - 117
  • [8] New global optimization algorithm for training feedforward neural networks and its application
    Li, Huan-Qin
    Wan, Bai-Wu
    [J]. Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice, 2003, 23 (08):
  • [9] A FAST AND ROBUST LEARNING ALGORITHM FOR FEEDFORWARD NEURAL NETWORKS
    WEYMAERE, N
    MARTENS, JP
    [J]. NEURAL NETWORKS, 1991, 4 (03) : 361 - 369
  • [10] A FAST NEW ALGORITHM FOR TRAINING FEEDFORWARD NEURAL NETWORKS
    SCALERO, RS
    TEPEDELENLIOGLU, N
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1992, 40 (01) : 202 - 210
12345