Back to overview

Bayesian Networks with Imprecise Probabilities: Theory and Application to Classification.

Type of publication Peer-reviewed
Publikationsform Contribution to book (peer-reviewed)
Author Corani Giorgio, Antonucci Alessandro, Zaffalon Marco,
Project Multi Model Inference for dealing with uncertainty in environmental models
Show all

Contribution to book (peer-reviewed)

Book Data Mining: Foundations and Intelligent Paradigms
Editor , Holmes E. D.; , Lakhmi J.C.
Publisher Springer, Berlin
Page(s) 49 - 93
ISBN 978-3-642-23240-4
Title of proceedings Data Mining: Foundations and Intelligent Paradigms


Bayesian networks are powerful probabilistic graphical models for modelling uncertainty. Among others, classification represents an important application: some of the most used classifiers are based on Bayesian networks. Bayesian networks are precise models: exact numeric values should be provided for quantification. This requirement is sometimes too narrow. Sets instead of single distributions can provide a more realis- tic description in these cases. Bayesian networks can be generalized to cope with sets of distributions. This leads to a novel class of imprecise probabilistic graphical models, called credal networks. In particular, classifiers based on Bayesian networks are generalized to so-called credal classifiers. Unlike Bayesian classifiers, which always detect a single class as the one maximizing the posterior class probability, a credal classifier may eventually be unable to discriminate a single class. In other words, if the available information is not sufficient, credal classifiers allow for indecision between two or more classes, this providing a less informative but more robust conclusion than Bayesian classifiers.