An effective learning of neural network by using RFBP learning algorithm

被引：19

作者：

Chen, YJ

Huang, TC

Hwang, RC ^{[1
]}

机构：

[1] I Shou Univ, Dept Elect Engn, Kaohsiung 84008, Taiwan

[2] Cheng Shiu Univ, Dept Ind Engn & Management, Kaohsiung 833, Taiwan

[3] Natl Sun Yat Sen Univ, Dept Elect Engn, Kaohsiung 804, Taiwan

来源：

INFORMATION SCIENCES | 2004年 / 167卷 / 1-4期

关键词：

effective learning; local minimum; neural network; randorn fuzzy back-propagation; classification;

D O I：

10.1016/j.ins.2003.10.012

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, an effective learning of neural network by using random fuzzy back-propagation (RFBP) learning algorithm is developed. Based on this new learning algorithm, neural network not only has an accurate learning capability, but also can increase the probability of escaping from the local minimum while neural network is training. For demonstrating the new algorithm we developed has its outperformance, the classifications of the non-convex in two dimensions (NC2) problem are simulated. For comparison, the same simulations by using conventional back-propagation (BP) learning algorithm with constant pairs of learning rate (alpha = 0.1-0.9) and momentum (xi = 0.1-0.9) and stochastic BP learning are also performed. (C) 2003 Elsevier Inc. All rights reserved.

引用

页码：77 / 86

页数：10

共 16 条

[1] RADAR SIGNAL CATEGORIZATION USING A NEURAL NETWORK [J].

ANDERSON, JA ;

GATELY, MT ;

PENZ, PA ;

COLLINS, DR .

PROCEEDINGS OF THE IEEE, 1990, 78 (10) :1646-1657

[2] NEURAL NETWORKS AND PRINCIPAL COMPONENT ANALYSIS - LEARNING FROM EXAMPLES WITHOUT LOCAL MINIMA [J].

BALDI, P ;

HORNIK, K .

NEURAL NETWORKS, 1989, 2 (01) :53-58

[3] NONLINEAR-SYSTEM IDENTIFICATION USING NEURAL NETWORKS [J].

CHEN, S ;

BILLINGS, SA ;

GRANT, PM .

INTERNATIONAL JOURNAL OF CONTROL, 1990, 51 (06) :1191-1214

[4] A stochastic backpropagation algorithm for training neural networks [J].

Chen, YQ ;

Yin, T ;

Babri, HA .

ICICS - PROCEEDINGS OF 1997 INTERNATIONAL CONFERENCE ON INFORMATION, COMMUNICATIONS AND SIGNAL PROCESSING, VOLS 1-3: THEME: TRENDS IN INFORMATION SYSTEMS ENGINEERING AND WIRELESS MULTIMEDIA COMMUNICATIONS, 1997, :703-707

[5] The application of neural networks to the papermaking industry [J].