Hierarchical Mixtures of Experts and the EM Algorithm

dc.creator	Jordan, Michael I.
dc.creator	Jacobs, Robert A.
dc.date	2004-10-20T20:49:48Z
dc.date	2004-10-20T20:49:48Z
dc.date	1993-08-01
dc.date.accessioned	2013-10-09T02:48:33Z
dc.date.available	2013-10-09T02:48:33Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1440
dc.identifier	CBCL-083
dc.identifier	http://hdl.handle.net/1721.1/7206
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM's). Learning is treated as a maximum likelihood problem; in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. We also develop an on-line learning algorithm in which the parameters are updated incrementally. Comparative simulation results are presented in the robot dynamics domain.
dc.format	29 p.
dc.format	190144 bytes
dc.format	678911 bytes
dc.format	application/octet-stream
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1440
dc.relation	CBCL-083
dc.subject	supervised learning
dc.subject	statistics
dc.subject	decision trees
dc.subject	neuralsnetworks
dc.title	Hierarchical Mixtures of Experts and the EM Algorithm

Files in this item

Files	Size	Format	View
There are no files associated with this item.