Foundations of probabilistic inference with uncertain evidence

摘要: The application of formal inference procedures, such as Bayes Theorem, requires that a judgment is made, by which the evidential meaning physical observations stated within context model. Uncertain evidence defined class for this statement cannot take place in certain terms. It significant evidence, since it be treated using Theorem its conventional form [G. Shafer, A Mathematical Theory Evidence, Princeton University Press, Princeton, NJ, 1976]. In paper, we present an extension Bayesian theory can used to perform probabilistic with uncertain evidence. based on idealized view are rule out possible valuations variables modeling space. different from earlier approaches Jeffrey's probability kinematics and Cheeseman's distributed meaning, introducing two forms representation presented, non-probabilistic analogues found theories Evidence Possibility Theory. By viewing separate step process, clear interpretation given these representation, generalization derived. This generalized allows incorporated into procedures.