A kind of BP neural network algorithm based on grey interval

被引：8

作者：

Wu, Shun-Xiang ^{[1
]}

Luo, De-Lin ^{[1
]}

Zhou, Zhi-Wen ^{[1
]}

Cai, Jian-Huai ^{[1
]}

Shi, Yeu-Xiang ^{[2
]}

机构：

[1] Xiamen Univ, Dept Automat, Xiamen 361005, Peoples R China

[2] Xiangtan Univ, Key Lab Intelligent Manufacture Hunan Prov, Xiangtan 411105, Peoples R China

来源：

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE | 2011年 / 42卷 / 03期

关键词：

neural network; grey system; generalisation; grey interval; PERFORMANCE;

D O I：

10.1080/00207720903513582

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

080201 [机械制造及其自动化];

摘要：

In order to improve the learning ability of a forward neural network, in this article, we incorporate the feedback back-propagation (FBBP) and grey system theory to consider the learning and training of a neural network new perspective. By reducing the input grey degree we optimise the input of the neural network to make it more rational for learning and training of neural networks. Simulation results verified the efficiency of the proposed algorithm by comparing its performance with that of FBBP and classic back-propagation (BP). The results showed that the proposed algorithm has the characteristics of fast training and strong ability of generalisation and it is an effective learning method.

引用

页码：389 / 396

页数：8

共 29 条

[1]

DONG CH, 2007, MATLAB NEURAL NETWOR, P12904

[2]

Performance improvement of backpropagation algorithm by automatic activation function gain tuning using fuzzy logic [J].

Eom, K ;

Jung, K ;

Sirisena, H .

NEUROCOMPUTING, 2003, 50 :439-460

[3]

GAO J, 2003, PRINCIPLE ARTIFICIAL

[4]

ISHIBUCHI H, 1998, INT JOINT C NEUR NET

[5]

KARABATAK M, 2008, EXPERT SYSTEMS APPL, DOI DOI 10.1016/J.ESWA.02.064

[6]

KUMAR S, 2006, NEURAL NETWORKS, V8

[7]

Li S.Y., 2004, ENG FUZZY MATH ITS A

[8]

Predicting motor vehicle crashes using Support Vector Machine models [J].

Li, Xiugang ;

Lord, Dominique ;

Zhang, Yunlong ;

Me, Yuanchang .

ACCIDENT ANALYSIS AND PREVENTION, 2008, 40 (04) :1611-1618

[9]

LIU SF, 2005, GREY SYSTEM THEORY I, V6

[10]

Inverting feedforward neural networks using linear and nonlinear programming [J].

Lu, BL ;

Kita, H ;

Nishikawa, Y .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (06) :1271-1290

← 1 2 3 →