A Probabilistic Network of Predicates
This work addresses a foundational problem in probabilistic modeling for AI researchers, offering a novel representation to overcome propositional and acyclic constraints.
The authors tackled the limitations of Bayesian networks by proposing a probabilistic network with nodes as unary predicates that can include directed cycles, enabling representation of domain knowledge in a static network and handling cyclic causal tendencies and recursive plans.
Bayesian networks are directed acyclic graphs representing independence relationships among a set of random variables. A random variable can be regarded as a set of exhaustive and mutually exclusive propositions. We argue that there are several drawbacks resulting from the propositional nature and acyclic structure of Bayesian networks. To remedy these shortcomings, we propose a probabilistic network where nodes represent unary predicates and which may contain directed cycles. The proposed representation allows us to represent domain knowledge in a single static network even though we cannot determine the instantiations of the predicates before hand. The ability to deal with cycles also enables us to handle cyclic causal tendencies and to recognize recursive plans.