Utilize este identificador para referenciar este registo: http://hdl.handle.net/1822/839

TítuloLamarckian training of feedforward neural networks
Autor(es)Cortez, Paulo
Rocha, Miguel
Neves, José
Palavras-chaveGenetic and evolutionary Algorithms
Feedforward neural Networks
Lamarckian optimization
DataAbr-2001
EditoraMichel Verleysen
CitaçãoVERLEYSEN, Michel, ed. lit. – “European Symposium on Artificial Neural Networks : proceedings, 9, Bruges, 2001”. Brussels: D-Facto, 2001. p. 153-158.
Resumo(s)Living creatures improve their adaptation capabilities to a changing world by means of two orthogonal processes: evolution and lifetime learning. Within Artificial Intelligence, both mechanisms inspired the development of non-orthodox problem solving tools, namely Genetic and Evolutionary Algorithms (GEAs) and Artificial Neural Networks (ANNs). Several local search gradient-based methods have been developed for ANN training, with considerable success; however, in some situations, such procedures may lead to local minima. Under this scenario, the combination of evolution and learning techniques, may lead to better results (e.g., global optima). Comparative tests on several Machine Learning tasks attest this claim.
TipoconferencePaper
URIhttp://hdl.handle.net/1822/839
Arbitragem científicayes
AcessoopenAccess
Aparece nas coleções:DSI - Engenharia da Programação e dos Sistemas Informáticos
DI/CCTC - Artigos (papers)
CAlg - Artigos em livros de atas/Papers in proceedings

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
lamarck.pdf170,84 kBAdobe PDFVer/Abrir

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu Currículo DeGóis