On cautious probabilistic inference and default detachment

On cautious probabilistic inference and default detachment

0.00 Avg rating0 Votes
Article ID: iaor19952337
Country: Switzerland
Volume: 55
Issue: 1
Start Page Number: 195
End Page Number: 224
Publication Date: May 1995
Journal: Annals of Operations Research
Authors: , ,
Abstract:

Conditional probabilities are one promising and widely used approach to model uncertainty in information systems. This paper discusses the DUCK-calculus, which is founded on the cautious approach to uncertain probabilistic inference. Based on a set of sound inference rules, derived probabilistic information is gained by local bounds propagation techniques. Precision being always a certral point of criticism to such systems, the authors demonstrate that DUCK need not necessarily suffer from these problems. They can show that the popular Bayesian networks are subsumed by DUCK, implying that precise probabilities can be deduced by local propagation techniques, even in the multiply connected case. A comparative study with INFERNO and with inference techniques based on global operations-research techniques yields quite favorable results for the present approach. Since conditional probabilities are also suited to model nonmonotonic situations by considering different contexts, the authors investigate the problems of maximal and relevant contexts, needed to draw default conclusions about individuals.

Reviews

Required fields are marked *. Your email address will not be published.