Fine-tuning artificial neural networks automatically

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2007

Autores

Francisco Reinaldo (Autor) FEUP; Rui Camacho (Autor) FEUP; Luís P. Reis (Autor) FEUP; Demétrio Renó Magalhães (Autor) Outra

Ata de Conferência Internacional

Título: EUROPEAN COMPUTING CONFERENCE

Páginas: 39-43

EUROPEAN COMPUTING CONFERENCE

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Engenharia electrotécnica, electrónica e informática

CORDIS: Ciências Tecnológicas > Engenharia > Engenharia do conhecimento

Outras Informações

DOI: 10.1007/978-0-387-84814-3_5

Abstract (EN): To get the most out of powerful tools expert knowledge is often required. Experts are the ones with the suitable knowledge to tune the tools¿ parameters. In this paper we assess several techniques which can automatically fine tune ANN parameters. Those techniques include the use of GA and Stratified Sampling. The tuning includes the choice of the best ANN structure and the best network biases and their weights. Empirical results achieved in experiments performed using nine heterogeneous data sets show that the use of the proposed Stratified Sampling technique is advantageous.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 5