Hill-climbing and branch-and-bound algorithms for exact and approximate inference in credal networks

Cano Utrera, Andrés; Gómez Olmedo, Manuel; Moral Callejón, Serafín; Abellán Mulero, Joaquín

doi:10.1016/j.ijar.2006.07.020

1-s2.0-S0888613X06000971-main.pdf (399.3Kb)

Identificadores

URI: https://hdl.handle.net/10481/77902

DOI: 10.1016/j.ijar.2006.07.020

Exportar

Editorial

Elsevier

Materia

Credal network

Probability intervals

Bayesian networks

Strong independence

Hill-climbing

Branch-and-bound algorithms

Inteligencia artificial

Artificial intelligence

Fecha

2006-09-29

Referencia bibliográfica

Andrés Cano... [et al.]. Hill-climbing and branch-and-bound algorithms for exact and approximate inference in credal networks, International Journal of Approximate Reasoning, Volume 44, Issue 3, 2007, Pages 261-280, ISSN 0888-613X, [https://doi.org/10.1016/j.ijar.2006.07.020]

Patrocinador

TIN2004-06204-C03-02

Resumen

This paper proposes two new algorithms for inference in credal networks. These algorithms enable probability intervals to be obtained for the states of a given query variable. The first algorithm is approximate and uses the hill-climbing technique in the Shenoy–Shafer architecture to propagate in join trees; the second is exact and is a modification of Rocha and Cozman’s branch-and-bound algorithm, but applied to general directed acyclic graphs.

Colecciones

DCCIA - Comunicaciones Congresos, Conferencias, ...

Excepto si se señala otra cosa, la licencia del ítem se describe como Attribution-NonCommercial-NoDerivatives 4.0 Internacional