Defining Explanation in Probabilistic Systems
Abstract
As probabilistic systems gain popularity and are coming into wider use, the need for a mechanism that explains the system's findings and recommendations becomes more critical. The system will also need a mechanism for ordering competing explanations. We examine two representative approaches to explanation in the literature-- one due to Gardenfors and one due to Pearl--and show that both suffer from significant problems. We propose an approach to defining a notion of "better explanation" that combines some of the features of both together with more recent work by Pearl and others on causality.
Cite
Text
Chajewska and Halpern. "Defining Explanation in Probabilistic Systems." Conference on Uncertainty in Artificial Intelligence, 1997.Markdown
[Chajewska and Halpern. "Defining Explanation in Probabilistic Systems." Conference on Uncertainty in Artificial Intelligence, 1997.](https://mlanthology.org/uai/1997/chajewska1997uai-defining/)BibTeX
@inproceedings{chajewska1997uai-defining,
title = {{Defining Explanation in Probabilistic Systems}},
author = {Chajewska, Urszula and Halpern, Joseph Y.},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {1997},
pages = {62-71},
url = {https://mlanthology.org/uai/1997/chajewska1997uai-defining/}
}