Inscrição na biblioteca: Guest
Journal of Automation and Information Sciences

Publicou 12 edições por ano

ISSN Imprimir: 1064-2315

ISSN On-line: 2163-9337

SJR: 0.173 SNIP: 0.588 CiteScore™:: 2

Indexed in

Multiobjective Optimization of Evolving Feedforward Neural Networks

Volume 46, Edição 11, 2014, pp. 9-22
DOI: 10.1615/JAutomatInfScien.v46.i11.20
Get accessGet access

RESUMO

The paper has proposed to utilize a multicriteria approach to training evolutionary feedforward neural networks. The general structure of such neural networks is considered. A comparative analysis of single-objective, scalarized multiobjective learning and Pareto-based multiobjective learning is performed. Simulation in the presence of noisy measurements with different distribution laws has confirmed the effectiveness of the suggested approach.

Portal Digital Begell Biblioteca digital da Begell eBooks Diários Referências e Anais Coleções de pesquisa Políticas de preços e assinaturas Begell House Contato Language English 中文 Русский Português German French Spain