Uncertain logical gates in possibilistic networks: Theory and application to human geography

Abstract : Possibilistic networks offer a qualitative approach for modeling epistemic uncertainty. Their practical implementation requires the specification of conditional possibility tables, as in the case of Bayesian networks for probabilities. The elicitation of probability tables by experts is made much easier by means of noisy logical gates that enable multidimensional tables to be constructed from the knowledge of a few parameters. This paper presents the possibilistic counterparts of usual noisy connectives (and, or, max, min,. . .). Their interest and limitations are illustrated on an example taken from a human geography model-ing problem. The difference of behavior between probabilistic and possibilistic connectives is discussed in detail. Results in this paper may be useful to bring possibilistic networks closer to applications.
Type de document :
Article dans une revue
International Journal of Approximate Reasoning, Elsevier, 2017, 82, pp.101 - 118. <10.1016/j.ijar.2016.11.009>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01445519
Contributeur : Andrea G. B. Tettamanzi <>
Soumis le : mercredi 25 janvier 2017 - 08:43:08
Dernière modification le : vendredi 27 janvier 2017 - 01:04:48

Fichier

uncertain-logical-gates.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Didier Dubois, Giovanni Fusco, Henri Prade, Andrea G. B. Tettamanzi. Uncertain logical gates in possibilistic networks: Theory and application to human geography. International Journal of Approximate Reasoning, Elsevier, 2017, 82, pp.101 - 118. <10.1016/j.ijar.2016.11.009>. <hal-01445519>

Partager

Métriques

Consultations de
la notice

105

Téléchargements du document

29