Extremal Optimization Combined with LM Gradient Search for MLP Network Learning

DOI

10.2991/ijcis.2010.3.5.11How to use a DOI?

Keywords

Back propagation; Extremal optimization; “Levenberg–Marquardt” (LM) gradient search; Memetic Algorithms; Supervised learning

Abstract

Gradient search based neural network training algorithm may suffer from local optimum, poor generalization and slow convergence. In this study, a novel Memetic Algorithm based hybrid method with the integration of “extremal optimization” and “Levenberg–Marquardt” is proposed to train multilayer perceptron (MLP) networks. Inheriting the advantages of the two approaches, the proposed “EO-LM” method can avoid local minima and improve MLP network learning performance in generalization capability and computation efficiency. The experimental tests on two benchmark problems and an application example for the end-point-prediction of basic oxygen furnace in steelmaking show the effectiveness of the proposed EO-LM algorithm.

Copyright

© 2010, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - Peng Chen
AU  - Yu-Wang Chen
AU  - Yong-Zai Lu
PY  - 2010
DA  - 2010/10/01
TI  - Extremal Optimization Combined with LM Gradient Search for MLP Network Learning
JO  - International Journal of Computational Intelligence Systems
SP  - 622
EP  - 631
VL  - 3
IS  - 5
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.2010.3.5.11
DO  - 10.2991/ijcis.2010.3.5.11
ID  - Chen2010
ER  -