Parameter estimation in large causal models

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

The assessment of a probability distribution that is associated with a Bayesian network is a challenging task, even if its topology is sparse. Special probability distributions, based on the notion of causal independence, have therefore been proposed, as these allow defining a probability distribution in terms of Boolean combinations of local distributions. In Bayesian networks which need to model a large number of interactions among causal mechanisms even this approach becomes infeasible. We investigate the use of equivalence classes of binomial distributions as a means to define such very large Bayesian networks.

Original languageEnglish
Title of host publicationECAI 2004 -
Subtitle of host publicationProceedings of the 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems (PAIS 2004)
EditorsRamon Lopez de Mantaras, Lorenza Saitta
PublisherIOS
Pages1037-1038
Number of pages2
ISBN (Electronic)9781586034528
Publication statusPublished - 2004
Externally publishedYes
Event16th European Conference on Artificial Intelligence, ECAI 2004 - Valencia, Spain
Duration: 22 Aug 200427 Aug 2004
Conference number: 16

Publication series

NameFrontiers in Artificial Intelligence and Applications
PublisherIOS Press
Volume110
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference16th European Conference on Artificial Intelligence, ECAI 2004
Abbreviated titleECAI
Country/TerritorySpain
CityValencia
Period22/08/0427/08/04

Fingerprint

Dive into the research topics of 'Parameter estimation in large causal models'. Together they form a unique fingerprint.

Cite this