In the probabilistic approach to uncertainty management the input knowledge is usually represented by means of some probability distributions. In this paper we assume that the input knowledge is given by two discrete conditional probability distributions, represented by two stochastic matrices P and Q. The consistency of the knowledge base is analyzed. Coherence conditions and explicit formulas for the extensions to marginal distributions are obtained in some special cases.
Knowledge integration for conditional probability assessments / Gilio, Angelo; Spezzaferri, Fulvio. - STAMPA. - (1992), pp. 98-103. (Intervento presentato al convegno 8th Conf. on Uncertainty in Artificial Intelligence tenutosi a Stanford Univ., Stanford, CA nel July 17-19, 1992).
Knowledge integration for conditional probability assessments
GILIO, ANGELO;SPEZZAFERRI, Fulvio
1992
Abstract
In the probabilistic approach to uncertainty management the input knowledge is usually represented by means of some probability distributions. In this paper we assume that the input knowledge is given by two discrete conditional probability distributions, represented by two stochastic matrices P and Q. The consistency of the knowledge base is analyzed. Coherence conditions and explicit formulas for the extensions to marginal distributions are obtained in some special cases.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
