×

zbMATH — the first resource for mathematics

Mean field theory for sigmoid belief networks. (English) Zbl 0900.68379
Summary: 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.

MSC:
68T10 Pattern recognition, speech recognition
PDF BibTeX XML Cite
Full Text: Link