Mean Field Theory for Sigmoid Belief Networks
Author(s)Saul, Lawrence K.; Jaakkola, Tommi; Jordan, Michael I.
MetadataShow full item record
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.