A Study of Associative Evidential Reasoning
Abstract
Evidential reasoning is cast as the problem of simplifying the evidence-hypothesis relation and constructing combination formulas that possess certain testable properties. Important classes of evidence as identifiers, annihilators, and idempotents and their roles in determining binary operations on intervals of reals are discussed. The appropriate way of constructing formulas for combining evidence and their limitations, for instance, in robustness, are presented.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2013
- DOI:
- 10.48550/arXiv.1304.2740
- arXiv:
- arXiv:1304.2740
- Bibcode:
- 2013arXiv1304.2740C
- Keywords:
-
- Computer Science - Artificial Intelligence
- E-Print:
- Appears in Proceedings of the Third Conference on Uncertainty in Artificial Intelligence (UAI1987)