UNSPECIFIED (1999) Geometry, moments and Bayesian networks with hidden variables. In: 7th International Workshop on Artificial Intelligence and Statistics (Uncertainty 99), JAN 03-06, 1999, FT LAUDERDALE, FL.

Full text not available from this repository.

Abstract

The purpose of this paper is to present a systematic way of analysing the geometry of the probability spaces for a particular class of Bayesian networks with hidden variables. It will be shown that the conditional independence statements implicit in such graphical models can be neatly expressed as simple polynomial relationships among central moments. This algebraic framework will enable us to explore and identify the structural constraints on the sample space induced by models with tree strcutures and therefore characterise the families of distributions consistent with such conditional independence assumptions.

Item Type:	Conference Item (UNSPECIFIED)
Subjects:	Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software Q Science > QA Mathematics
Journal or Publication Title:	ARTIFICIAL INTELLIGENCE AND STATISTICS 99, PROCEEDINGS
Publisher:	MORGAN KAUFMANN PUB INC
ISBN:	1-55860-589-4
Editor:	Heckerman, D and Whittaker, J
Date:	1999
Number of Pages:	6
Page Range:	pp. 293-298
Publication Status:	Published
Title of Event:	7th International Workshop on Artificial Intelligence and Statistics (Uncertainty 99)
Location of Event:	FT LAUDERDALE, FL
Date(s) of Event:	JAN 03-06, 1999
URI:	http://wrap.warwick.ac.uk/id/eprint/12694

Data sourced from Thomson Reuters' Web of Knowledge

Request changes to a record

Actions (login required)

View Item