Mean Field Theory for Sigmoid Belief Networks
L.K. Saul, Tommi Jaakkola, Michael I. Jordan · Journal of Artificial Intelligence Research · 1996
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.