Evolving artificial neural networks using an improved PSO and DPSO

被引：164

作者：

Yu, Jianbo ^{[1
]}

Wang, Shijin ^{[1
]}

Xi, Lifeng ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Dept Ind Engn & Management, Shanghai 200240, Peoples R China

来源：

NEUROCOMPUTING | 2008年 / 71卷 / 4-6期

基金：

中国国家自然科学基金;

关键词：

artificial neural network; particle swarm optimization; evolution strategies;

D O I：

10.1016/j.neucom.2007.10.013

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 presents an improved particle swarm optimization (PSO) and discrete PSO (DPSO) with an enhancement operation by using a self-adaptive evolution strategies (ES). This improved PSO/DPSO is proposed for joint optimization of three-layer feedforward artificial neural network (ANN) structure and parameters (weights and bias), which is named ESPNet. The experimental results on two real-world problems show that ESPNet can produce compact ANNs with good generalization ability. (c) 2007 Elsevier B.V. All rights reserved.

引用

页码：1054 / 1060

页数：7

共 18 条

[1]

Abbass H. A., 2001, LECT NOTES ARTIF INT, V2256, P1

[2] An Overview of Evolutionary Algorithms for Parameter Optimization [J].

Baeck, Thomas ;

Schwefel, Hans-Paul .

EVOLUTIONARY COMPUTATION, 1993, 1 (01) :1-23

[3] G-Prop: Global optimization of multilayer perceptrons using GAs [J].

Castillo, PA ;

Merelo, JJ ;

Prieto, A ;

Rivas, V ;

Romero, G .

NEUROCOMPUTING, 2000, 35 :149-163

[4] 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

[5]

Kennedy J, 1997, IEEE SYS MAN CYBERN, P4104, DOI 10.1109/ICSMC.1997.637339

[6]

Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968

[7]

Liu Y, 2000, IEEE T EVOLUT COMPUT, V4, P380, DOI 10.1109/4235.887237

[8] Application of evolutionary neural network method in predicting pollutant levels in downtown area of Hong Kong [J].

Lu, WZ ;

Fan, HY ;

Lo, SM .

NEUROCOMPUTING, 2003, 51 :387-400

[9]

MURPHYAND PM, 1994, UCI REPOSITORY MACHI

[10] Mutation-based genetic neural network [J].

Palmes, PP ;

Hayasaka, T ;

Usui, S .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2005, 16 (03) :587-600

← 1 2 →