Equivalent Characterization of a Class of Conditional Probabilistic Independencies
- 569 Downloads
Markov networks utilize nonembedded probabilistic conditional independencies in order to provide an economical representation of a joint distribution in uncertainty management. In this paper we study several properties of nonembedded conditional independencies and show that they are in fact equivalent. The results presented here not only show the useful characteristics of an important subclass of probabilistic conditional independencies, but further demonstrate the relationship between relational theory and probabilistic reasoning.
KeywordsConditional Independency Joint Probability Distribution Fact Equivalent Bayesian Belief Network Markov Network
Unable to display preview. Download preview PDF.
- 5.Hajek, P., Havranek, T., Jirousek, R.: Uncertain Information Processing in Expert Systems. CRC Press. (1992)Google Scholar
- 6.Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann. San Francisco, California. (1988)Google Scholar
- 7.Shafer, G.: An Axiomatic Study of Computation in Hypertrees. University of Kansas. School of Business Working Papers (232). (1991)Google Scholar
- 8.Studeny, M.: Conditional Independence Relations Have No Finite Complete Characterization. Eleventh Prague Conference on Information Theory, Statistical Decision Foundation and Random Processes. (1990)Google Scholar
- 9.Wong, S.K.M., Wang, Z.W.: On Axiomatization of Probabilistic Conditional Independence. Tenth Conference on Uncertainty in Artificial Intelligence. (1994) 591–597Google Scholar
- 10.Wong, S.K.M., Butz, C.J., Xiang, Y.: A Method for Implementing a Probabilistic Model as a Relational Database. Eleventh Conference on Uncertainty in Artificial Intelligence. (1995) 556–564Google Scholar
- 11.Wong, S.K.M.: Testing Implication of Probabilistic Dependencies. Twelfth Conference on Uncertainty in Artificial Intelligence. (1996) 545–553Google Scholar
- 12.Wong, S.K.M.: The Relational Structure of Belief Networks. (submitted for publication) (1997)Google Scholar