English   español  
Por favor, use este identificador para citar o enlazar a este item: http://hdl.handle.net/10261/127467
COMPARTIR / IMPACTO:
Estadísticas
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:
Título

Online EM with weight-based forgetting

AutorCelaya, Enric ; Agostini, Alejandro
Palabras claveForgetting factor
On-line EM
Local representations
Biased sampling
NGnet
Fecha de publicación2015
EditorMassachusetts Institute of Technology
CitaciónNeural Computation 27(5): 1142-1157 (2015)
ResumenIn the online version of the EM algorithm introduced by Sato and Ishii (2000), a time-dependent discount factor is introduced for forgetting the effect of the old estimated values obtained with an earlier, inaccurate estimator. In their approach, forgetting is uniformly applied to the estimators of each mixture component depending exclusively on time, irrespective of theweight attributed to each unit for the observed sample. This causes an excessive forgetting in the less frequently sampled regions. To address this problem, we propose a modification of the algorithm that involves a weight-dependent forgetting, different for each mixture component, in which old observations are forgotten according to the actual weight of the new samples used to replace older values. A comparison of the timedependent versus the weight-dependent approach shows that the latter improves the accuracy of the approximation and exhibits much greater stability.
Versión del editorhttp://dx.doi.org/10.1162/NECO_a_00723
URIhttp://hdl.handle.net/10261/127467
DOI10.1162/NECO_a_00723
Identificadoresdoi: 10.1162/NECO_a_00723
issn: 0899-7667
e-issn: 1530-888X
Aparece en las colecciones: (IRII) Artículos
Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
On-lineEM.pdf483,38 kBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro completo
 

Artículos relacionados:


NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.