Title :
Computational models for probabilistic reasoning in expert systems
Author_Institution :
Dept. of Comput. Sci., Heriot-Watt Univ., Edinburgh, UK
Abstract :
Numerous methods have been suggested and used for dealing with uncertainty in expert systems. Work in theoretical statistics has shown that it is possible to adopt sound probabilistic approaches to uncertain inference in expert systems. The author considers two approaches: the first uses Bayesian inference without assuming independence and the second is based on causal graphs, or more correctly termed `influence diagrams´
Keywords :
Bayes methods; expert systems; graph theory; inference mechanisms; probabilistic logic; Bayesian inference; causal graphs; computational models; expert systems; independence; influence diagrams; probabilistic approaches; probabilistic reasoning; theoretical statistics; uncertain inference;
Conference_Titel :
Reasoning Under Uncertainty, IEE Colloquium on
Conference_Location :
London
