Particle swarms for feedforward neural network training

被引：208

作者：

Mendes, R ^{[1
]}

Cortez, P ^{[1
]}

Rocha, M ^{[1
]}

Neves, J ^{[1
]}

机构：

[1] Univ Minho, Dept Informat, P-4719 Braga, Portugal

来源：

PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3 | 2002年

关键词：

Evolutionary Programming; Feedforward Neural Networks; gradient-based algorithms; Particle Swarm Optimization;

D O I：

10.1109/IJCNN.2002.1007808

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Particle Swarm. is a novel optimization paradigm for real-valued functions, based on the social dynamics of group interaction. In this work, it is proposed its application to the training of Neural Networks. Comparative tests were carried out, for classification and regression tasks, being the results compared with other approaches.

引用

页码：1895 / 1899

页数：3

共 19 条

[1]

BERGH F, 2000, SACJ SART, P84

[2]

Bransen J, 1995, PROCEEDINGS OF THE EIGHTH INTERNATIONAL KANT CONGRESS, VOL II, PT 1, SECT 1-9, P145

[3]

CLERC M, 2002, IN PRESS IEEE T EV C

[4]

CORTEZ P, 2001, P INT S AD SYST EV C

[5]

Dobbins R., 1996, Computational Intelligence PC Tools

[6]

Fogel L., 1999, INTELLIGENCE SIMULAT

[7]

Haykin S., 1999, Neural Networks: A Comprehensive Foundation, V2nd ed

[8]

HCIN T, 1998, P 2 INT C KNOWL BAS, P596

[9]

Kenndy J., 1995, P IEEE INT C NEUR NE, V4, P1942, DOI [10.4018/ijmfmp.2015010104, DOI 10.4018/IJMFMP.2015010104]

[10]

Kennedy J., 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406), P1931, DOI 10.1109/CEC.1999.785509

← 1 2 →