English

Mean Field Theory for Sigmoid Belief Networks

Artificial Intelligence 2009-09-25 v1

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.

Keywords

Cite

@article{arxiv.cs/9603102,
  title  = {Mean Field Theory for Sigmoid Belief Networks},
  author = {L. K. Saul and T. Jaakkola and M. I. Jordan},
  journal= {arXiv preprint arXiv:cs/9603102},
  year   = {2009}
}

Comments

See http://www.jair.org/ for any accompanying files