Mean Field Theory for Sigmoid Belief Networks
dc.date.accessioned | 2004-10-08T20:36:26Z | |
dc.date.accessioned | 2018-11-24T10:21:23Z | |
dc.date.available | 2004-10-08T20:36:26Z | |
dc.date.available | 2018-11-24T10:21:23Z | |
dc.date.issued | 1996-08-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6652 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/6652 | |
dc.description.abstract | 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. | en_US |
dc.format.extent | 269766 bytes | |
dc.format.extent | 412589 bytes | |
dc.language.iso | en_US | |
dc.title | Mean Field Theory for Sigmoid Belief Networks | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AIM-1570.pdf | 412.5Kb | application/pdf | View/ |
AIM-1570.ps | 269.7Kb | application/postscript | View/ |