A Novel Hybrid Optimization Method with Application in Cascade-Correlation Neural Network Training

Author

Gao, X.Z. ; Wang, X. ; Ovaska, S.J.

Author_Institution

Dept. of Electr. Eng., Helsinki Univ. of Technol., Espoo

fYear

2008

fDate

10-12 Sept. 2008

Firstpage

793

Lastpage

800

Abstract

In this paper, based on the fusion of the clonal selection algorithm (CSA) and differential evolution (DE) method, we propose a novel optimization scheme: CSA-DE. The DE is employed here to increase the affinities of the clones of the antibodies (Abs) in the CSA. Several nonlinear functions are used to verify and demonstrate the effectiveness of this hybrid optimization approach. It is further applied for the construction of the cascade-correlation (C-C) neural network, in which the optimal hidden nodes can be obtained.

Keywords

artificial immune systems; learning (artificial intelligence); neural nets; artificial immune system; cascade-correlation neural network training; clonal selection algorithm; differential evolution method; hybrid optimization method; nonlinear function; Cloning; Computational modeling; Convergence; Electronic mail; Genetic mutations; Hybrid intelligent systems; Immune system; Neural networks; Optimization methods; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Hybrid Intelligent Systems, 2008. HIS '08. Eighth International Conference on

Conference_Location

Barcelona

Print_ISBN

978-0-7695-3326-1

Electronic_ISBN

978-0-7695-3326-1

Type

conf

DOI

10.1109/HIS.2008.19

Filename

4626728