Nonlinear System Identification with Composite Relevance Vector Machines
dc.contributor.author | Camps Valls, Gustavo | |
dc.contributor.author | Martínez Ramón, Manel | |
dc.contributor.author | Rojo-Álvarez, José Luis | |
dc.contributor.author | Muñoz Marí, Jordi | |
dc.date.accessioned | 2009-02-04T15:39:57Z | |
dc.date.available | 2009-02-04T15:39:57Z | |
dc.date.issued | 2007-01-01 | |
dc.identifier.issn | 1070-9908 | |
dc.identifier.uri | http://hdl.handle.net/10115/1910 | |
dc.description.abstract | Nonlinear system identification based on relevance vector machines (RVMs) has been traditionally addressed by stacking the input and/or output regressors and then performing standard RVM regression. This letter introduces a full family of composite kernels in order to integrate the input and output information in the mapping function efficiently and hence generalize the standard approach. An improved trade-off between accuracy and sparsity is obtained in several benchmark problems. Also, the RVM yields confidence intervals for the predictions, and it is less sensitive to free parameter selection. | es |
dc.language.iso | en | es |
dc.relation.ispartofseries | IEEE Signal Processing Letters | es |
dc.relation.ispartofseries | 14(4) | es |
dc.rights | Atribución-NoComercial-SinDerivadas 3.0 España | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/3.0/es/ | * |
dc.subject | Telecomunicaciones | es |
dc.title | Nonlinear System Identification with Composite Relevance Vector Machines | es |
dc.type | info:eu-repo/semantics/article | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.subject.unesco | 3325 Tecnología de las Telecomunicaciones | es |
dc.description.departamento | Teoría de la Señal y Comunicaciones |
Files in this item
This item appears in the following Collection(s)
-
Artículos de Revista [3651]
Except where otherwise noted, this item's license is described as Atribución-NoComercial-SinDerivadas 3.0 España