A munin network for the median nerve-a case study on loops
Applied Artificial Intelligence
Local conditioning in Bayesian networks
Artificial Intelligence
Representations and algorithms for efficient inference in bayesian networks
Representations and algorithms for efficient inference in bayesian networks
Exploiting causal independence in Bayesian network inference
Journal of Artificial Intelligence Research
Lazy propagation in junction trees
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Independence of causal influence and clique tree propagation
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Context-specific independence in Bayesian networks
UAI'96 Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence
Hi-index | 0.01 |
The efficiency of algorithms for probabilistic inference in Bayesian networks can be improved by exploiting independence of causal influence In this paper we propose a method to exploit independence of causal influence based on on-line construction of decomposition trees. The efficiency of inference is improved by exploiting independence relations induced by evidence during decomposition tree construction. We also show how a factorized representation of independence of causal influence can be derived from a local expression language. The factorized representation is shown to fit ideally with the lazy propagation framework. Empirical results indicate that considerable efficiency improvements can be expected if either the decomposition trees are constructed on-line or the factorized representation is used.