Generalizations of Boolean algebras. An attribute exploration
In this paper, we generalize the noisy-or model. The generalizations are three-fold. First, we allow parents to be multivalued ordinal variables. Second, parents can have both positive and negative influences on their common child. Third, we describe how the suggested generalization can be extended to multivalued child variables. The major advantage of our generalizations is that they require only one parameter per parent. We suggest a model learning method and report results of experiments on the...
Möbius transformation is an important tool for establishing weights of compositional expert systems rules from conditional weights. In this paper, an applicability of Möbius transformation of rule bases is also extended to knowledge bases with elementary disjunctions in antecedents of rules. This paper contains an existence theorem, an algorithm of the transformation and some open problems which tend to maximal generality as well.