Abstract
We adapt the theory of descriptive complexity to encompass Bayesian networks, so as to quantify the expressivity of Bayesian network specifications based on predicates and quantifiers. We show that Bayesian network specifications that employ firstorder quantification capture the complexity class PP; by allowing quantification over predicates, the resulting Bayesian network specifications capture ...NP each class in the hierarchy PPNP , a result tha does not seem to have equivalent in the literature.1