Evolving Neural Networks Using Differential Evolution with Neighborhood-Based Mutation and Simple Subpopulation Scheme

Author

Mineu, Nicole L. ; Silva, Adenilton J da ; Ludermir, Teresa B.

Author_Institution

Inst. de Cienc. Mat. e de Comput., Univ. de Sao Paulo, Sao Carlos, Brazil

fYear

2012

fDate

20-25 Oct. 2012

Firstpage

190

Lastpage

195

Abstract

This paper presents a method to search for near optimal neural networks. The proposed method combines Differential Evolution with Global and Local Neighborhood (DEGL) evolutionary algorithm and the multimodal technique Simple Subpopulation Scheme (SSS). The performance of the proposed method is investigated through experiments on six machine learning benchmarks for classification problems. The proposed method is competitive when compared to other methods of literature.

Keywords

evolutionary computation; learning (artificial intelligence); neural nets; pattern classification; DEGL evolutionary algorithm; SSS; classification problems; differential evolution; global-and-local neighborhood evolutionary algorithm; machine learning benchmarks; multimodal technique simple subpopulation scheme; near optimal neural networks; neighborhood-based mutation scheme; Artificial neural networks; Biological neural networks; Equations; Mathematical model; Sociology; Statistics; Vectors; Differential Evolution; artificial neural networks; hybrid intelligent systems; simple subpopulation scheme;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks (SBRN), 2012 Brazilian Symposium on

Conference_Location

Curitiba

ISSN

1522-4899

Print_ISBN

978-1-4673-2641-4

Type

conf

DOI

10.1109/SBRN.2012.43

Filename

6374847