Mean Field Theory for Sigmoid Belief Networks

dc.creator	Saul, Lawrence K.
dc.creator	Jaakkola, Tommi
dc.creator	Jordan, Michael I.
dc.date	2004-10-08T20:36:26Z
dc.date	2004-10-08T20:36:26Z
dc.date	1996-08-01
dc.date.accessioned	2013-10-09T02:46:22Z
dc.date.available	2013-10-09T02:46:22Z
dc.date.issued	2013-10-09
dc.identifier	AIM-1570
dc.identifier	http://hdl.handle.net/1721.1/6652
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	We develop a mean field theory for sigmoid belief networks based on ideas from statistical mechanics. Our mean field theory provides a tractable approximation to the true probability distribution in these networks; it also yields a lower bound on the likelihood of evidence. We demonstrate the utility of this framework on a benchmark problem in statistical pattern recognition -- the classification of handwritten digits.
dc.format	269766 bytes
dc.format	412589 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-1570
dc.title	Mean Field Theory for Sigmoid Belief Networks

Files in this item

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