Towards Jointree Propagation with Conditional Probability Distributions
In this paper, we suggest a novel approach to jointree computation. Unlike all previous jointree methods, we propose that jointree computation should use conditional probability distributions rather than potentials. One salient feature of this approach is that the exact form of the messages to be transmitted throughout the network can be identified a priori. Consequently, irrelevant messages can be ignored, while relevant messages can be computed more efficiently. We discuss four advantages of our jointree propagation method.
KeywordsBayesian Network Leaf Node Marginal Distribution Directed Acyclic Graph Chordal Graph
Unable to display preview. Download preview PDF.
- 4.Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)Google Scholar
- 5.Shafer, G.: Probabilistic Expert Systems, Society for Industrial and Applied Mathematics (1996)Google Scholar
- 8.Xiang, Y.: Probabilistic Reasoning in Multiagent Systems, Cambridge (2002)Google Scholar