Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Artificial Intelligence
Multivalued dependencies and a new normal form for relational databases
ACM Transactions on Database Systems (TODS)
Graphical Belief Modeling
Formal Properties of Conditional Independence in Different Calculi of AI
ECSQARU '93 Proceedings of the European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty
Irrelevance and Independence Axioms in Quasi-Bayesian Theory
ECSQARU '95 Proceedings of the European Conference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty
Hi-index | 0.00 |
In this paper, we study different concepts of conditional belief functions independence in the context of the transferable belief model. We especially clarify the relationships between the concepts of conditional non-interactivity, irrelevance and doxastic independence. Conditional non-interactivity is defined by the 'mathematical' property useful for computation considerations and corresponds to decomposionality of the belief functions. Conditional irrelevance is defined by a 'common sense' property based on conditioning. Conditional doxastic independence is defined by a particular form of irrelevance, the one preserved under Dempster's rule of combination.