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.
Original language | American English |
---|---|
Pages | 153-160 |
Number of pages | 8 |
State | Published - 1 Dec 2005 |
Externally published | Yes |
Event | Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence, UAI 2005 - Duration: 1 Dec 2005 → … |
Conference
Conference | Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence, UAI 2005 |
---|---|
Period | 1/12/05 → … |