Evaulation of Uncertain Inference Models I: PROSPECTOR
Abstract
This paper examines the accuracy of the PROSPECTOR model for uncertain reasoning. PROSPECTOR's solutions for a large number of computer-generated inference networks were compared to those obtained from probability theory and minimum cross-entropy calculations. PROSPECTOR's answers were generally accurate for a restricted subset of problems that are consistent with its assumptions. However, even within this subset, we identified conditions under which PROSPECTOR's performance deteriorates.
Cite
Text
Yadrick et al. "Evaulation of Uncertain Inference Models I: PROSPECTOR." Conference on Uncertainty in Artificial Intelligence, 1986. doi:10.1016/B978-0-444-70396-5.50013-3Markdown
[Yadrick et al. "Evaulation of Uncertain Inference Models I: PROSPECTOR." Conference on Uncertainty in Artificial Intelligence, 1986.](https://mlanthology.org/uai/1986/yadrick1986uai-evaulation/) doi:10.1016/B978-0-444-70396-5.50013-3BibTeX
@inproceedings{yadrick1986uai-evaulation,
title = {{Evaulation of Uncertain Inference Models I: PROSPECTOR}},
author = {Yadrick, Robert M. and Perrin, Bruce M. and Vaughan, David S. and Holden, Peter D. and Kempf, Karl G.},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {1986},
pages = {77-88},
doi = {10.1016/B978-0-444-70396-5.50013-3},
url = {https://mlanthology.org/uai/1986/yadrick1986uai-evaulation/}
}