Thoughts on belief and model revision with uncertain evidence

0106215 - UTIA-B 20040025 CZ eng K - Conference Paper (Czech conference)
Vomlel, Jiří
Thoughts on belief and model revision with uncertain evidence.
Znalosti 2004. Sborník příspěvků 3.ročníku konference. Ostrava: VŠB TU, 2004 - (Snášel, V.), s. 126-137. ISBN 80-248-0456-5.
[Znalosti 2004 /3./. Brno (CZ), 22.02.2004-25.02.2004]
R&D Projects: GA ČR GA201/02/1269
Institutional research plan: CEZ:AV0Z1075907
Keywords : probabilistic models * Bayesian networks * belief revision
Subject RIV: BD - Theory of Information

Bayesian networks and other graphical probabilistic models became a popular framework for reasoning with uncertainty. Efficient methods have been developed for revising beliefs with new evidence. However, when the evidence is uncertain, i.e. represented by a probability distribution, different methods have been proposed. In this paper we analyze and compare these methods. The goal is to show in what cases they can be used correctly.
Permanent Link: http://hdl.handle.net/11104/0013397