Dynamic construction of belief networks

Abstract-We describe a method for incrementally constructing belief networks, which are directed acyclic graph representations for probability distributions. We have developed a network-construction language (FRAIW), which is similar to a fonvard-chaining language using data dependencies but has additional features for specifying distributions. A particularly important feature of this language is that it allows the user to conveniently specify conditional probability matrices using stereotyped models of intercausal interaction. Using FRAIW, one can define pa-rameterized classes of probabilistic models. These parameterized models make it possible to apply probabilistic reasoning to problems for which it is impractical to have a single large, static model