Paper

F. J. Díez and J. Mira. Distributed inference in Bayesian networks. Cybernetics and Systems, 25 (1994) 36-61.

17 pages. PostScript (198 KB), zip version (60 KB), BibTeX entry.

Abstract

Bayesian networks originated as a framework for distributed reasoning. In singly-connected networks, there exists an elegant inference algorithm that can be implemented in parallel having a processor for every node. It can be extended to take profit of the OR--gate, a model of interaction among causes which simplifies knowledge acquisition and evidence propagation. We also discuss two exact and one approximate methods for dealing with general networks. It will be shown how all these algorithms admit distributed implementations.