A Probabilistic Reasoning Environment
This work addresses the challenge of automated probabilistic reasoning for AI systems, but it appears incremental as it builds on existing Bayesian network methods without claiming major breakthroughs.
The paper tackles the problem of constructing and revising belief networks by introducing a three-level framework for probabilistic argument, resulting in a system that supports dynamic belief propagation, evidence assimilation, and network evaluation.
A framework is presented for a computational theory of probabilistic argument. The Probabilistic Reasoning Environment encodes knowledge at three levels. At the deepest level are a set of schemata encoding the system's domain knowledge. This knowledge is used to build a set of second-level arguments, which are structured for efficient recapture of the knowledge used to construct them. Finally, at the top level is a Bayesian network constructed from the arguments. The system is designed to facilitate not just propagation of beliefs and assimilation of evidence, but also the dynamic process of constructing a belief network, evaluating its adequacy, and revising it when necessary.