This paper describes RISO, an implementation of distributed belief network software. Distributed belief networks are a natural extension of ordinary belief networks in which the belief network is composed of subnetworks running on separate processors. In keeping with the distributed computational model, no single processor has information about the structure of the entire distributed belief network, and inferences are to be computed using only local quantities. A general policy is proposed for publishing information as belief networks. A modeling language for the representation of distributed belief networks has been devised, and software has been implemented to compile the modeling language and carry out inferences. Belief networks may contain arbitrary conditional distributions, and new types of distributions can be defined without modifying the existing inference software. In inference, an exact result is computed if a rule is known for combining incoming partial results, and if an exact result is not known, an approximation is computed on the fly -- this scheme allows the belief networks to directly represent the distributions that arise in practice. Some features of Java, the implementation language, have been found to be extremely useful, namely the classloader and Remote Method Invocation. The paper concludes with a small example which shows how a monitoring system can be implemented as a distributed belief network.
[1]
Yang Xiang,et al.
Learning Belief Networks in Domains with Recursively Embedded Pseudo Independent Submodels
,
1997,
UAI.
[2]
Enrique F. Castillo,et al.
Expert Systems and Probabilistic Network Models
,
1996,
Monographs in Computer Science.
[3]
Dan Geiger,et al.
Approximation Algorithms for the Loop Cutset Problem
,
1994,
UAI.
[4]
R. T. Cox.
Probability, frequency and reasonable expectation
,
1990
.
[5]
Yang Xiang,et al.
Exploring Parallelism in Learning Belief Networks
,
1997,
UAI.
[6]
Walter R. Gilks,et al.
A Language and Program for Complex Bayesian Modelling
,
1994
.
[7]
李幼升,et al.
Ph
,
1989
.
[8]
Robert Orchard,et al.
IDS: Improving Aircraft Fleet Maintenance
,
1997,
AAAI/IAAI.
[9]
Judea Pearl,et al.
Probabilistic reasoning in intelligent systems
,
1988
.
[10]
Yang Xiang,et al.
A Probabilistic Framework for Cooperative Multi-Agent Distributed Interpretation and Optimization of Communication
,
1996,
Artif. Intell..
[11]
Robert E. Tarjan,et al.
Self-adjusting binary search trees
,
1985,
JACM.
[12]
Glenn Shafer,et al.
Readings in Uncertain Reasoning
,
1990
.