Computer Science – Artificial Intelligence
Scientific paper
2008-04-15
Computer Science
Artificial Intelligence
7 pages, 1 figure
Scientific paper
Markov networks and Bayesian networks are effective graphic representations of the dependencies embedded in probabilistic models. It is well known that independencies captured by Markov networks (called graph-isomorphs) have a finite axiomatic characterization. This paper, however, shows that independencies captured by Bayesian networks (called causal models) have no axiomatization by using even countably many Horn or disjunctive clauses. This is because a sub-independency model of a causal model may be not causal, while graph-isomorphs are closed under sub-models.
No associations
LandOfFree
Causal models have no complete axiomatic characterization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Causal models have no complete axiomatic characterization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Causal models have no complete axiomatic characterization will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-653716