Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/120
Título: | Adaptive learning in changing environments |
Autor(es): | Rocha, Miguel Cortez, Paulo Neves, José |
Palavras-chave: | Baldwin Effect Evolutionary Programming Hybrid Systems Lamarckian Optimization Multi-Layer Perceptrons |
Data: | Abr-2003 |
Editora: | d-side publishing |
Citação: | In M. Verleysen Ed., Proceedings of 11th European Symposium on Artificial Neural Networks (ESANN'2003), Bruges, Belgium, pp. 487-492 |
Resumo(s): | The remarkable adaptation of living creatures to their environments comes as a result of the interaction of two orthogonal processes: evolution and learning. Within the Machine Learning arena, both mechanisms inspired the development of the Evolutionary and Connectionist Computation fields, which can be combined under two different views, the Lamarckian and Baldwinian approaches. Comparative tests reward the latter when changing environments are considered. |
Tipo: | Artigo em ata de conferência |
URI: | https://hdl.handle.net/1822/120 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | DI/CCTC - Artigos (papers) DSI - Engenharia da Programação e dos Sistemas Informáticos |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
baldwin.pdf | 231,8 kB | Adobe PDF | Ver/Abrir |