Reasoning and Learning in Probabilistic and Possibilistic Networks: An Overview
Abstract
Graphical modelling is a powerful framework for reasoning under uncertainty. We give an overview on the semantical background and relevant properties of probabilistic and possibilistic networks, respectively, and consider knowledge representation and independence as well as evidence propagation and learning such networks from data. Whereas Bayesian networks and Markov networks are well-known for a couple of years, we also outline the perspectives of possibilistic networks as a tool for the efficient information-compressed treatment of uncertain and imprecise knowledge.
Cite
Text
Gebhardt and Kruse. "Reasoning and Learning in Probabilistic and Possibilistic Networks: An Overview." European Conference on Machine Learning, 1995. doi:10.1007/3-540-59286-5_45Markdown
[Gebhardt and Kruse. "Reasoning and Learning in Probabilistic and Possibilistic Networks: An Overview." European Conference on Machine Learning, 1995.](https://mlanthology.org/ecmlpkdd/1995/gebhardt1995ecml-reasoning/) doi:10.1007/3-540-59286-5_45BibTeX
@inproceedings{gebhardt1995ecml-reasoning,
title = {{Reasoning and Learning in Probabilistic and Possibilistic Networks: An Overview}},
author = {Gebhardt, Jörg and Kruse, Rudolf},
booktitle = {European Conference on Machine Learning},
year = {1995},
pages = {3-16},
doi = {10.1007/3-540-59286-5_45},
url = {https://mlanthology.org/ecmlpkdd/1995/gebhardt1995ecml-reasoning/}
}