Decomposable negation normal form
Journal of the ACM (JACM)
A survey on knowledge compilation
AI Communications
Journal of Artificial Intelligence Research
On valued negation normal form formulas
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Compiling Bayesian networks with local structure
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
A comparative study of compilation-based inference methods for min-based possibilistic networks
ECSQARU'13 Proceedings of the 12th European conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
A generic framework for a compilation-based inference in probabilistic and possibilistic networks
Information Sciences: an International Journal
Hi-index | 0.00 |
Graphical models are important tools for representing and analyzing uncertain information. Diverse inference methods were developed for efficient computations in these models. In particular, compilation-based inference has recently triggered much research, especially in the probabilistic and the possibilistic frameworks. Even though the inference process follows the same principle in the two frameworks, it depends strongly on the specificity of each of them, namely in the interpretation of handled values (probability\possibility) and appropriate operators (*\min and +\max). This paper emphasizes on common points and unveils differences between the compilation-based inference process in the probabilistic and the possibilistic setting from a spatial viewpoint.