Evidence Absorption and Propagation Through Evidence Reversals
Abstract
The arc reversal/node reduction approach to probabilistic inference is extended to include the case of instantiated evidence by an operation called "evidence reversal." This not only provides a technique for computing posterior joint distributions on general belief networks, but also provides insight into the methods of Pearl [1986b] and Lauritzen and Spiegelhalter [1988]. Although it is well understood that the latter two algorithms are closely related, in fact all three algorithms are identical whenever the belief network is a forest.
Cite
Text
Shachter. "Evidence Absorption and Propagation Through Evidence Reversals." Conference on Uncertainty in Artificial Intelligence, 1989.Markdown
[Shachter. "Evidence Absorption and Propagation Through Evidence Reversals." Conference on Uncertainty in Artificial Intelligence, 1989.](https://mlanthology.org/uai/1989/shachter1989uai-evidence/)BibTeX
@inproceedings{shachter1989uai-evidence,
title = {{Evidence Absorption and Propagation Through Evidence Reversals}},
author = {Shachter, Ross D.},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {1989},
url = {https://mlanthology.org/uai/1989/shachter1989uai-evidence/}
}