Bayesian networks for continuous values and uncertainty in the learning process

This paper proposes a method for Bayesian networks that handles uncertainty and discretization of continuous variables when learning the networks from a database of cases. The database is reorganised in a new form of representation called reduced database where data are treated as distributions on symbolic values.

• Type: Conference
• Year: 2003
• Where: EUSFLAT
• Authors: J. F. Baldwin, E. Di Tomaso
• Keywords: Bayesian Networks, Continuous Variables, Database, EUSFLAT 2003, EUSFLAT 2007