On Convergence Properties of the EM Algorithm for Gaussian Mixtures

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/7195

Full metadata record

DC Field	Value	Language
dc.creator	Jordan, Michael	-
dc.creator	Xu, Lei	-
dc.date	2004-10-20T20:49:25Z	-
dc.date	2004-10-20T20:49:25Z	-
dc.date	1995-04-21	-
dc.date.accessioned	2013-10-09T02:48:31Z	-
dc.date.available	2013-10-09T02:48:31Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1520	-
dc.identifier	CBCL-111	-
dc.identifier	http://hdl.handle.net/1721.1/7195	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	"Expectation-Maximization'' (EM) algorithm and gradient-based approaches for maximum likelihood learning of finite Gaussian mixtures. We show that the EM step in parameter space is obtained from the gradient via a projection matrix $P$, and we provide an explicit expression for the matrix. We then analyze the convergence of EM in terms of special properties of $P$ and provide new results analyzing the effect that $P$ has on the likelihood surface. Based on these mathematical results, we present a comparative discussion of the advantages and disadvantages of EM and other algorithms for the learning of Gaussian mixture models.	-
dc.format	9 p.	-
dc.format	291671 bytes	-
dc.format	476864 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1520	-
dc.relation	CBCL-111	-
dc.subject	learning	-
dc.subject	neural networks	-
dc.subject	EM algorithm	-
dc.subject	clustering	-
dc.subject	mixture models	-
dc.subject	statistics	-
dc.title	On Convergence Properties of the EM Algorithm for Gaussian Mixtures	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI