Belief Updating and Learning in Semi-Qualitative Probabilistic Networks
Abstract
This paper explores semi-qualitative probabilistic networks (SQPNs) that combine numeric and qualitative information. We first show that exact inferences with SQPNs are NPPP-Complete. We then show that existing qualitative relations in SQPNs (plus probabilistic logic and imprecise assessments) can be dealt effectively through multilinear programming. We then discuss learning: we consider a maximum likelihood method that generates point estimates given a SQPN and empirical data, and we describe a Bayesian-minded method that employs the Imprecise Dirichlet Model to generate set-valued estimates.
Cite
Text
de Campos and Cozman. "Belief Updating and Learning in Semi-Qualitative Probabilistic Networks." Conference on Uncertainty in Artificial Intelligence, 2005.Markdown
[de Campos and Cozman. "Belief Updating and Learning in Semi-Qualitative Probabilistic Networks." Conference on Uncertainty in Artificial Intelligence, 2005.](https://mlanthology.org/uai/2005/decampos2005uai-belief/)BibTeX
@inproceedings{decampos2005uai-belief,
title = {{Belief Updating and Learning in Semi-Qualitative Probabilistic Networks}},
author = {de Campos, Cassio Polpo and Cozman, Fábio Gagliardi},
booktitle = {Conference on Uncertainty in Artificial Intelligence},
year = {2005},
pages = {153-160},
url = {https://mlanthology.org/uai/2005/decampos2005uai-belief/}
}