Please use this identifier to cite or link to this item: http://hdl.handle.net/1822/353

TitleA Lamarckian Approach for Neural Network Training
Author(s)Cortez, Paulo
Rocha, Miguel
Neves, José
Keywordsfeedforward neural networks
genetic and evolutionary algorithms
hybrid systems
lamarckian optimization
learning algorithms
Issue date2002
PublisherSpringer
JournalNeural Processing Letters
Citation"Neural Processing Letters". 15:2 (2002) 105-116.
Abstract(s)In Nature, living beings improve their adaptation to surrounding environments by means of two main orthogonal processes: evolution and lifetime learning. Within the Artificial Intelligence arena, both mechanisms inspired the development of non-orthodox problem solving tools, namely: Genetic and Evolutionary Algorithms (GEAs) and Artificial Neural Networks (ANNs). In the past, several gradient-based methods have been developed for ANN training, with considerable success. However, in some situations, these may lead to local minima in the error surface. Under this scenario, the combination of evolution and learning techniques may induce better results, desirably reaching global optima. Comparative tests that were carried out with classification and regression tasks, attest this claim.
TypeArticle
DescriptionProva tipográfica (In Press).
URIhttp://hdl.handle.net/1822/353
DOI10.1023/A:1015259001150
ISSN1370-4621
Publisher versionThe original publication is available at www.springerlink.com
Peer-Reviewedyes
AccessRestricted access (UMinho)
Appears in Collections:CAlg - Artigos em revistas internacionais/Papers in international journals
DI/CCTC - Artigos (papers)
DSI - Engenharia da Programação e dos Sistemas Informáticos

Files in This Item:
File Description SizeFormat 
lamnpl2.pdf
  Restricted access
270,91 kBAdobe PDFView/Open

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 ORCID