Mean Field Theory for Sigmoid Belief Networks

作者：L.K. Saul, Tommi Jaakkola, Michael I. Jordan · 发表于：Journal of Artificial Intelligence Research · 年份：1996 · DOI：10.1613/jair.251 · 被引用次数：339 · 研究领域：Bayesian Modeling and Causal Inference、Machine Learning and Algorithms、Machine Learning and Data Classification

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.