Does the Wake-sleep Algorithm Produce Good Density Estimators?

NIPS 1995: Proceedings of the 8th International Conference on Neural Information Processing Systems

Volumn , Issue , 1995, Pages 661-667

  Frey, Brendan J ^a   Hinton, Geoffrey E ^a   Dayan, Peter ^b  

^a UNIVERSITY OF TORONTO   (Canada)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLUSTERING ALGORITHMS; MONTE CARLO METHODS; PROBABILITY DISTRIBUTIONS; SLEEP RESEARCH; STOCHASTIC MODELS; STOCHASTIC SYSTEMS;

BOTTOM UP; DENSITY ESTIMATOR; GENERATIVE MODEL; HIDDEN UNITS; HIGH DIMENSIONAL DATA; PROBABILITY: DISTRIBUTIONS; SIMPLE++; STOCHASTICS; SYNTHETIC AND REAL DATA; TOPDOWN;

WAKES;

EID: 85156256883     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Dayan, P., Hinton, G. E., Neal, R. M., and Zemel, R. S. 1995. The Helmholtz machine. Neural Computation 7, 889-904.
2. Dempster, A. P., Laird, N. M. and Rubin, D. B. 1977. Maximum likelihood from incomplete data via the EM algorithm. J. Royal Statistical Society, Series B 34, 1-38.
3. Gailly, J. 1993. gzip program for unix.
4. Hinton, G. E., Dayan, P., Frey, B. J., Neal, R. M. 1995. The wake-sleep algorithm for unsupervised neural networks. Science 268, 1158-1161.
5. Neal, R. M. 1992. Connectionist learning of belief networks. Artificial Intelligence 56, 71-113.
6. Saul, L. K., Jaakkola, T, and Jordan, M. I. 1996. Mean field theory for sigmoid belief networks. Submitted to Journal of Artificial Intelligence.