Training Method for a Feed Forward Neural Network Based on Meta-heuristics

被引：0

作者：

Melo, Haydee ^{[1
]}

Zhang, Huiming ^{[1
]}

Vasant, Pandian ^{[2
]}

Watada, Junzo ^{[3
]}

机构：

[1] Waseda Univ, Grad Sch Prod Informat & Syst, Tokyo, Japan

[2] Univ Teknol PETRONAS, Fundamental & Appl Sci Dept, Seri Iskandar, Malaysia

[3] Univ Teknol PETRONAS, Deparment Comp & Informat Sci, Seri Iskandar, Malaysia

来源：

ADVANCES IN INTELLIGENT INFORMATION HIDING AND MULTIMEDIA SIGNAL PROCESSING, PT II | 2018年 / 82卷

关键词：

Particle Swarm Optimization; Neural network; Training algorithm; Gaussian distribution; Cauchy distribution;

D O I：

10.1007/978-3-319-63859-1_46

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes a Gaussian-Cauchy Particle Swarm Optimization (PSO) algorithm to provide the optimized parameters for a Feed Forward Neural Network. The improved PSO trains the Neural Network by optimizing the network weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian-Cauchy PSO Neural Network converges faster and is immune to local minima.

引用

页码：378 / 385

页数：8

共 8 条

[1]

[Anonymous], 2000, J STAT SOFTW

[2]

Cells M., 2002, The International Conference on Advances in Information Science and Soft Computing, P224

[3]

Cerqueira J. J. F., 2002, 2002 IEEE International Conference on Systems, Man and Cybernetics. Conference Proceedings (Cat. No.02CH37349), DOI 10.1109/ICSMC.2002.1176108

[4]

Eberhart R. C., 1998, Evolutionary Programming VII. 7th International Conference, EP98. Proceedings, P611, DOI 10.1007/BFb0040812

[5] Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks [J].

Gudise, VG ;

Venayagamoorthy, GK .

PROCEEDINGS OF THE 2003 IEEE SWARM INTELLIGENCE SYMPOSIUM (SIS 03), 2003, :110-117

[6] A Hybri of genetic algorithm and particle swarm optimization for recurrent network design [J].

Juang, CF .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (02) :997-1006

[7]

[王文娟 WANG Wenjuan], 2007, [西南石油大学学报, Journal of Southwestern Petroleum Institute. Natural Science Edition], V29, P31

[8] A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training [J].

Zhang, Jing-Ru ;

Zhang, Jun ;

Lok, Tat-Ming ;

Lyu, Michael R. .

APPLIED MATHEMATICS AND COMPUTATION, 2007, 185 (02) :1026-1037

← 1 →