Evolutionary design of neural networks for classification and regression

• Autor(es): Rocha, Miguel ; Cortez, Paulo, 1971- ; Neves, José
• Data: 2005
• Identificador Persistente: http://hdl.handle.net/1822/892
• Origem: RepositóriUM - Universidade do Minho
• Assunto(s): Supervised machine learning; Multilayer perceptrons; Evolutionary algorithms; Ensembles
• Tipo de Documento: Documento de conferência
• Idioma: Inglês

Descrição

Comunicação aprovada à ICANGA March 2005, Coimbra. The Multilayer Perceptrons (MLPs) are the most popular class of Neural Networks. When applying MLPs, the search for the ideal architecture is a crucial task, since it should should be complex enough to learn the input/output mapping, without overfitting the training data. Under this context, the use of Evolutionary Computation makes a promising global search approach for model selection. On the other hand, ensembles (combinations of models) have been boosting the performance of several Machine Learning (ML) algorithms. In this work, a novel evolutionary technique for MLP design is presented, being also used an ensemble based approach. A set of real world classification and regression tasks was used to test this strategy, comparing it with a heuristic model selection, as well as with other ML algorithms. The results favour the evolutionary MLP ensemble method.