Fast Learning by Bounding Likelihoods in Sigmoid Type Belief Networks

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

Volumn , Issue , 1995, Pages 528-534

  Jaakkola, Tommi ^a   Saul, Lawrence K ^a   Jordan, Michael I ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BAYESIAN NETWORKS; PARAMETER ESTIMATION; QUADRATIC PROGRAMMING;

EM ALGORITHMS; FAST LEARNING; HIDDEN UNITS; NETWORK PARAMETERS; NEURAL-NETWORKS; PROBABILISTIC INFORMATION; PROBABILISTICS; QUADRATIC OPTIMIZATION; SIGMOIDS; SUPERVISED LEARNING PROBLEMS;

NEURAL NETWORKS;

EID: 8644262205     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. P. Dayan, G. Hinton, R. Neal, and R. Zemel (1995). The helmholtz machine. Neurai Computation 7: 889-904.
2. A. Dempster, N. Laird, and D. Rubin. Maximum likelihood from incomplete data via the EM algorithm (1977). J. Roy. Statist. Soc. B 39:1-38.
3. G. Hinton, P. Dayan, B. Frey, and R. Neal (1995). The wake-sleep algorithm for unsupervised neural networks. Science 268: 1158-1161.
4. S. L. Lauritzen and D. J. Spiegelhalter (1988). Local computations with probabilities on graphical structures and their application to expert systems. J. Roy. Statist. Soc. 5 50:154-227.
5. R. Neal. Connectionist learning of belief networks (1992). Artificial Intelligence 56: 71-113.
6. J. Pearl (1988). Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann: San Mateo.
7. T. Petsche, A. Marcantonio, C. Darken, S. J. Hanson, G. M. Kuhn, I. Santoso (1995). A neural network autoassociator for induction motor failure prediction. In Advances in Neural Information Processing Systems 8. MIT Press.
8. L. K. Saul, T. Jaakkola, and M. I. Jordan (1995). Mean field theory for sigmoid belief networks. M. I. T. Computational Cognitive Science Technical Report 9501.