Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/102272
Type: Artigo de evento
Title: Hybrid Genetic Training Of Gated Mixtures Of Experts For Nonlinear Time Series Forecasting
Author: Coelho A.L.V.
Lima C.A.M.
Von Zuben F.J.
Abstract: In this paper, we introduce a genetic algorithm-based training mechanism (HGT-GAME) toward the automatic structural design and parameter configuration of Gated Mixtures of Experts (ME). In HGT-GAME, a whole ME instance is codified into a given chromosome. By employing regulatory genes, our approach enables the automatic pruning and growing of experts in a way to properly match the complexity of the task at hand. Moreover, to leverage HGT-GAME's effectiveness, a local search refinement upon each ME chromosome is performed in each generation via the gradient descent learning algorithm. Forecasting experiments evaluate the performance of Gated MEs trained with HGT-GAME.
Editor: 
Rights: fechado
Identifier DOI: 
Address: http://www.scopus.com/inward/record.url?eid=2-s2.0-0242552145&partnerID=40&md5=10a2bb464399904c6d69621b5f5b5ef2
Date Issue: 2003
Appears in Collections:Unicamp - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-0242552145.pdf451.62 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.