Mixed deterministic and probabilistic networks
- 1 November 2008
- journal article
- research article
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 54 (1-3) , 3-51
Abstract
The paper introduces mixed networks, a new graphical model framework for expressing and reasoning with probabilistic and deterministic information. The motivation to develop mixed networks stems from the desire to fully exploit the deterministic information (constraints) that is often present in graphical models. Several concepts and algorithms specific to belief networks and constraint networks are combined, achieving computational efficiency, semantic coherence and user-interface convenience. We define the semantics and graphical representation of mixed networks, and discuss the two main types of algorithms for processing them: inference-based and search-based. A preliminary experimental evaluation shows the benefits of the new model.Keywords
This publication has 20 references indexed in Scilit:
- AND/OR search spaces for graphical modelsArtificial Intelligence, 2007
- Compiling relational Bayesian networks for exact inferenceInternational Journal of Approximate Reasoning, 2006
- Unifying tree decompositions for reasoning in graphical modelsArtificial Intelligence, 2005
- Recursive conditioningArtificial Intelligence, 2001
- Bucket elimination: A unifying framework for reasoningArtificial Intelligence, 1999
- Turbo decoding as an instance of Pearl's "belief propagation" algorithmIEEE Journal on Selected Areas in Communications, 1998
- Probabilistic Horn abduction and Bayesian networksArtificial Intelligence, 1993
- HYBRID ALGORITHMS FOR THE CONSTRAINT SATISFACTION PROBLEMComputational Intelligence, 1993
- From knowledge bases to decision modelsThe Knowledge Engineering Review, 1992
- Network-based heuristics for constraint-satisfaction problemsArtificial Intelligence, 1987