Connectionist learning of belief networks

Artificial Intelligence

Volumn 56, Issue 1, 1992, Pages 71-113

  Neal, Radford M ^a  

^a UNIVERSITY OF TORONTO   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 44049116681     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/0004-3702(92)90065-6     Document Type: Article

References (22)

1. A learning algorithm for Boltzmann machines
2. Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition
3. AutoClass: a Bayesian classification system
4. Maximum likelihood from incomplete data via the EM algorithm (with discussion)
5. Variations on the Boltzmann machine learning algorithm
6. Sampling-based approaches to calculating marginal densities
7. Towards efficient probabilistic diagnosis in multiply connected belief networks
8. Learning and relearning in Boltzmann machines
9. Local computations with probabilities on graphical structures and their application to expert systems (with discussion)
10. An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition
11. Equation of state calculations by fast computing machines
12. Learning stochastic feedforward networks
13. Proceedings Conference on Influence Diagrams for Decision Analysis, Inference, and Prediction
14. Evidential reasoning using stochastic simulation of causal models
15. Learning representations by back-propagating errors
16. Probabilistic inference and influence diagrams
17. Sequential updating of conditional probabilities on directed graphical structures
18. An improved three-layer back propagation algorithm
19. Cross-validatory choice and assessment of statistical predictions (with discussion)
20. Mean field networks that learn to discriminate temporally distorted string