Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/8028
Título: | Evolution of neural networks for classification and regression |
Autor(es): | Rocha, Miguel Cortez, Paulo Neves, José |
Palavras-chave: | Supervised learning Multilayer perceptrons Evolutionary algorithms Lamarckian optimization Neural network ensembles |
Data: | 2007 |
Editora: | Elsevier 1 |
Revista: | Neurocomputing |
Citação: | "Neurocomputing". ISSN 0925-2312. 70:16-18 (Aug. 2007) 2809-2816. |
Resumo(s): | Although Artificial Neural Networks (ANNs) are important Data Mining techniques, the search for the optimal ANN is a challenging task: the ANN should learn the input-output mapping without overfitting the data and training algorithms may get trapped in local minima. The use of Evolutionary Computation (EC) is a promising alternative for ANN optimization. This work presents two hybrid EC/ANN algorithms: the first evolves neural topologies while the latter performs simultaneous optimization of architectures and weights. Sixteen real-world tasks were used to test these strategies. Competitive results were achieved when compared with a heuristic model selection and other Data Mining algorithms. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/8028 |
DOI: | 10.1016/j.neucom.2006.05.023 |
ISSN: | 0925-2312 |
Versão da editora: | http://www.sciencedirect.com/science/journal/09252312 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | CAlg - Artigos em revistas internacionais / Papers in international journals DI/CCTC - Artigos (papers) DSI - Engenharia da Programação e dos Sistemas Informáticos |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
enn3.pdf | Main article (pre-print) | 290,63 kB | Adobe PDF | Ver/Abrir |