Binarization algorithms for approximate updating in credal nets

dc.contributor.affiliationFGV
dc.contributor.authorAntonucci, Alessandro
dc.contributor.authorZaffalon, Marco
dc.contributor.authorIde, Jaime S.
dc.contributor.authorCozman, Fabio G.
dc.date.accessioned2018-05-10T13:35:50Z
dc.date.available2018-05-10T13:35:50Z
dc.date.issued2006
dc.descriptionConteúdo online de acesso restrito pelo editorpor
dc.description.abstractCredal networks generalize Bayesian networks relaxing numerical parameters. This considerably expands expressivity. but makes belief updating a hard task even on polytrees. Nevertheless, if all the variables are binary, polytree-shaped credal networks can be efficiently updated by the 2U algorithm. In this paper we present a binarization algorithm, that makes it possible to approximate an updating problem in a credal net by a corresponding problem in a credal net over binary variables. The procedure leads to outer bounds for the original problem. The binarized nets are in general multiply connected, but can be updated by the loopy variant of 2U. The quality of the overall approximation is investigated by promising numerical experiments.eng
dc.format.extentp. 1-19
dc.identifier.WoS000273476500011
dc.identifier.isbn978-1-58603-645-4
dc.identifier.issn0018-7267 / 1741-282X
dc.identifier.orcidIde, Jaime/0000-0002-7223-1102;
dc.identifier.researcheridIde, Jaime/B-6615-2014; Ide, Jaime/G-2738-2012
dc.identifier.urihttps://hdl.handle.net/10438/23152
dc.language.isoeng
dc.publisherIos Presseng
dc.relation.ispartofseriesStairs 2006eng
dc.rights.accessRightsrestrictedAccesseng
dc.sourceWeb of Science
dc.subjectBelief updatingeng
dc.subjectCredal networkseng
dc.subject2U algorithmeng
dc.subjectLoopy belief propagationeng
dc.subject.areaTecnologiapor
dc.subject.bibliodataAlgoritmospor
dc.titleBinarization algorithms for approximate updating in credal netseng
dc.typeConference Proceedingseng
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Nenhuma Miniatura disponível
Nome:
000273476500011.pdf
Tamanho:
176.91 KB
Formato:
Adobe Portable Document Format
Descrição: