Abstract—A criterion based on mutual information among variables is proposed for building a bayesian tree from a finite number of examples. The factor graph, in Forney-style form, can be used as an associative memory that performs probabilistic inference in data fusion applications. The procedure is explained with the aid of a fully-described example.
Building a Bayesian factor tree from examples / F., Palmieri; G., Romano; P., Salvo Rossi; Mattera, Davide. - STAMPA. - (2010), pp. 440-445. (Intervento presentato al convegno 2010 2nd International Workshop on Cognitive Information Processing (CIP) tenutosi a Isola d'Elba nel 14-16 giugno 2010) [10.1109/CIP.2010.5604232].
Building a Bayesian factor tree from examples
MATTERA, DAVIDE
2010
Abstract
Abstract—A criterion based on mutual information among variables is proposed for building a bayesian tree from a finite number of examples. The factor graph, in Forney-style form, can be used as an associative memory that performs probabilistic inference in data fusion applications. The procedure is explained with the aid of a fully-described example.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
