Mean Field Theory for Sigmoid Belief Networks

Lawrence K. Saul, Tommi S. Jaakkola, Michael I. Jordan

JAIR 1996 pp. 61-76

doi:10.1613/JAIR.251 /jair/1996/saul1996jair-mean/

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.

PDF JAIR Semantic Scholar

Cite

Text

Saul et al. "Mean Field Theory for Sigmoid Belief Networks." Journal of Artificial Intelligence Research, 1996. doi:10.1613/JAIR.251

Markdown

[Saul et al. "Mean Field Theory for Sigmoid Belief Networks." Journal of Artificial Intelligence Research, 1996.](https://mlanthology.org/jair/1996/saul1996jair-mean/) doi:10.1613/JAIR.251

BibTeX

@article{saul1996jair-mean,
  title     = {{Mean Field Theory for Sigmoid Belief Networks}},
  author    = {Saul, Lawrence K. and Jaakkola, Tommi S. and Jordan, Michael I.},
  journal   = {Journal of Artificial Intelligence Research},
  year      = {1996},
  pages     = {61-76},
  doi       = {10.1613/JAIR.251},
  volume    = {4},
  url       = {https://mlanthology.org/jair/1996/saul1996jair-mean/}
}