Does the Wake-Sleep Algorithm Produce Good Density Estimators?

Brendan J. Frey, Geoffrey E. Hinton, Peter Dayan

NeurIPS 1995 pp. 661-667

/neurips/1995/frey1995neurips-wakesleep/

Abstract

The wake-sleep algorithm (Hinton, Dayan, Frey and Neal 1995) is a rel(cid:173) atively efficient method of fitting a multilayer stochastic generative model to high-dimensional data. In addition to the top-down connec(cid:173) tions in the generative model, it makes use of bottom-up connections for approximating the probability distribution over the hidden units given the data, and it trains these bottom-up connections using a simple delta rule. We use a variety of synthetic and real data sets to compare the per(cid:173) formance of the wake-sleep algorithm with Monte Carlo and mean field methods for fitting the same generative model and also compare it with other models that are less powerful but easier to fit.

PDF NeurIPS Semantic Scholar

Cite

Text

Frey et al. "Does the Wake-Sleep Algorithm Produce Good Density Estimators?." Neural Information Processing Systems, 1995.

Markdown

[Frey et al. "Does the Wake-Sleep Algorithm Produce Good Density Estimators?." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/frey1995neurips-wakesleep/)

BibTeX

@inproceedings{frey1995neurips-wakesleep,
  title     = {{Does the Wake-Sleep Algorithm Produce Good Density Estimators?}},
  author    = {Frey, Brendan J. and Hinton, Geoffrey E. and Dayan, Peter},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {661-667},
  url       = {https://mlanthology.org/neurips/1995/frey1995neurips-wakesleep/}
}