FOURTH INTERNATIONAL SYMPOSIUM ON
IMPRECISE PROBABILITIES AND THEIR APPLICATIONS
Carnegie Mellon University
Pittsburgh, PA, USA
July 20-23 2005

ISIPTA'05 ELECTRONIC PROCEEDINGS

Andrés Cano, Manuel Gómez, Serafín Moral

Application of a hill-climbing algorithm to exact and approximate inference in credal networks

Abstract

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.

Keywords. Credal network, probability intervals, Bayesian networks, strong independence, hill-climbing and branch-and-bound algorithms.

Paper Download

The paper is availabe in the following formats:

Authors addresses:

Andrés Cano
Dpto. Ciencias de la Computaci�n e I.A.
ETS Ingenier�a Inform�tica
Avda. Andalucia s/n
Granada 18071
Spain

Manuel Gómez
Dpto. Ciencias de la Computación e I.A.
E.T.S. Ingeniería Informática
C// Periodista Daniel Saucedo Aranda
18071 Granada

Serafín Moral
Dpto. Ciencias de la Computación e IA
ETSI Informática
Universidad de Granada
18071 Granada - Spain

E-mail addresses:

Andrés Cano acu@decsai.ugr.es
Manuel Gómez mgomez@decsai.ugr.es
Serafín Moral smc@decsai.ugr.es

Related Web Sites


[ back to the Proceedings of ISIPTA'05 home page 
Send any remarks to the following address: smc@decsai.ugr.es