On the Detection of Conflicts in Diagnostic Bayesian Networks Using Abstraction
Young-Gyun Kim, Marco Valtorta
An important issue in the use of expert systems is the so-called brittleness problem. Expert systems model only a limited part of the world. While the explicit management of uncertainty in expert systems itigates the brittleness problem, it is still possible for a system to be used, unwittingly, in ways that the system is not prepared to address. Such a situation may be detected by the method of straw models, first presented by Jensen et al.  and later generalized and justified by Laskey . We describe an algorithm, which we have implemented, that takes as input an annotated diagnostic Bayesian network (the base model) and constructs, without assistance, a bipartite network to be used as a straw model. We show that in some cases this straw model is better that the independent straw model of Jensen et al., the only other straw model for which a construction algorithm has been designed and implemented.
Keywords: Diagnosis, Bayesian networks, abstraction, surprise, conflicts,
PS Link: ftp://ftp.cs.sc.edu/pub/valtorta/papers/tr9501.ps.gz
PDF Link: /papers/95/p362-kim.pdf
AUTHOR = "Young-Gyun Kim
and Marco Valtorta",
TITLE = "On the Detection of Conflicts in Diagnostic Bayesian Networks Using Abstraction",
BOOKTITLE = "Proceedings of the Eleventh Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-95)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "1995",
PAGES = "362--367"