A Variational Mean-Field Theory for Sigmoidal Belief Networks

Chiranjib Bhattacharyya, S. Sathiya Keerthi

NeurIPS 2000 pp. 374-380

/neurips/2000/bhattacharyya2000neurips-variational/

Abstract

A variational derivation of Plefka's mean-field theory is presented. This theory is then applied to sigmoidal belief networks with the aid of further approximations. Empirical evaluation on small scale networks show that the proposed approximations are quite com(cid:173) petitive.

PDF NeurIPS Semantic Scholar

Cite

Text

Bhattacharyya and Keerthi. "A Variational Mean-Field Theory for Sigmoidal Belief Networks." Neural Information Processing Systems, 2000.

Markdown

[Bhattacharyya and Keerthi. "A Variational Mean-Field Theory for Sigmoidal Belief Networks." Neural Information Processing Systems, 2000.](https://mlanthology.org/neurips/2000/bhattacharyya2000neurips-variational/)

BibTeX

@inproceedings{bhattacharyya2000neurips-variational,
  title     = {{A Variational Mean-Field Theory for Sigmoidal Belief Networks}},
  author    = {Bhattacharyya, Chiranjib and Keerthi, S. Sathiya},
  booktitle = {Neural Information Processing Systems},
  year      = {2000},
  pages     = {374-380},
  url       = {https://mlanthology.org/neurips/2000/bhattacharyya2000neurips-variational/}
}