Mean field theory for sigmoid belief networks
Mean field theory for sigmoid belief networks
复制标题
DOI:
10.1613/jair.251
复制
发表时间:
1996-01-01
影响因子:
5
通讯作者:
Jordan, MI
中科院分区:
文献类型:
--
作者:
Saul, LK;Jaakkola, T;Jordan, MI
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.