Please wait a minute...
FITEE
Front. Inform. Technol. Electron. Eng.  2012, Vol. 13 Issue (8): 585-592    DOI: 10.1631/jzus.C1200008
    
Negative effects of sufficiently small initial weights on back-propagation neural networks
Yan Liu, Jie Yang, Long Li, Wei Wu
School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China; School of Information Science and Engineering, Dalian Polytechnic University, Dalian 116034, China; Department of Mathematics and Computational Science, Hengyang Normal University, Hengyang 421002, China
Negative effects of sufficiently small initial weights on back-propagation neural networks
Yan Liu, Jie Yang, Long Li, Wei Wu
School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China; School of Information Science and Engineering, Dalian Polytechnic University, Dalian 116034, China; Department of Mathematics and Computational Science, Hengyang Normal University, Hengyang 421002, China
 全文: PDF 
摘要： In the training of feedforward neural networks, it is usually suggested that the initial weights should be small in magnitude in order to prevent premature saturation. The aim of this paper is to point out the other side of the story: In some cases, the gradient of the error functions is zero not only for infinitely large weights but also for zero weights. Slow convergence in the beginning of the training procedure is often the result of sufficiently small initial weights. Therefore, we suggest that, in these cases, the initial values of the weights should be neither too large, nor too small. For instance, a typical range of choices of the initial weights might be something like (?0.4, ?0.1)∪(0.1,0.4), rather than (?0.1, 0.1) as suggested by the usual strategy. Our theory that medium size weights should be used has also been extended to a few commonly used transfer functions and error functions. Numerical experiments are carried out to support our theoretical findings.
关键词： Neural networks;  Back-propagation;  Gradient learning method;  Convergence    
Abstract: In the training of feedforward neural networks, it is usually suggested that the initial weights should be small in magnitude in order to prevent premature saturation. The aim of this paper is to point out the other side of the story: In some cases, the gradient of the error functions is zero not only for infinitely large weights but also for zero weights. Slow convergence in the beginning of the training procedure is often the result of sufficiently small initial weights. Therefore, we suggest that, in these cases, the initial values of the weights should be neither too large, nor too small. For instance, a typical range of choices of the initial weights might be something like (?0.4, ?0.1)∪(0.1,0.4), rather than (?0.1, 0.1) as suggested by the usual strategy. Our theory that medium size weights should be used has also been extended to a few commonly used transfer functions and error functions. Numerical experiments are carried out to support our theoretical findings.
Key words: Neural networks    Back-propagation    Gradient learning method    Convergence
收稿日期: 2012-01-11 出版日期: 2012-08-02
CLC:  TP18  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Yan Liu
Jie Yang
Long Li
Wei Wu

引用本文:

Yan Liu, Jie Yang, Long Li, Wei Wu. Negative effects of sufficiently small initial weights on back-propagation neural networks. Front. Inform. Technol. Electron. Eng., 2012, 13(8): 585-592.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/jzus.C1200008    或    http://www.zjujournals.com/xueshu/fitee/CN/Y2012/V13/I8/585

[1] Bin Lin, Xiao-lang Yan, Zheng Shi, Yi-wei Yang. A sparse matrix model-based optical proximity correction algorithm with model-based mapping between segments and control sites[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(5): 436-442.
[2] Sahar Moghimi, Mohammad Hossein Miran Baygi, Giti Torkaman, Ehsanollah Kabir, Ali Mahloojifar, Narges Armanfard. Studying pressure sores through illuminant invariant assessment of digital color images[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(8): 598-606.
[3] Jian Bao, Yu Chen, Jin-shou Yu. A regeneratable dynamic differential evolution algorithm for neural networks with integer weights[J]. Front. Inform. Technol. Electron. Eng., 2010, 11(12): 939-947.