Mean-field methods for a special class of belief networks

Journal of Artificial Intelligence Research

Volumn 15, Issue , 2001, Pages 91-114

  Bhattacharyya, Chiranjib ^a   Keerthi, S Sathiya ^b  

^a INDIAN INSTITUTE OF SCIENCE   (India)

^b NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; COMPUTER NETWORKS;

BELIEF NETWORKS; MEAN-FIELD THEORY;

COMPUTATIONAL METHODS;

EID: 24044517971     PISSN: 10769757     EISSN: None     Source Type: Journal    
DOI: 10.1613/jair.734     Document Type: Article

References (28)

1. Ackley, D., Hinton, G., & Sejnowski, T. (1985). A learning algorithm for boltzmann machines. Cognitive Science, 9, 147-169.
2. Agosta, J. M. (1990). The structure of bayes networks for visual recognition. Uncertainity in Artificial Intelligence, 4.
3. Barber, D., & van de Laar, P. (1999). Variational cumulant expansion for intractable distributions. Journal of Artificial Intelligence Research, 10, 435-455.
4. Bhattacharyya, C., & Keerthi, S. S. (1999a). Mean-field theory for stochastic connectionist networks. Tech. rep. IISc-CSA-99-03, Department of Computer Science and Automation, Indian Institute of Science.
5. Bhattacharyya, C., & Keerthi, S. S. (1999b). Plefka's mean-field theory from a variational viewpoint. Submitted to IEEE Trans. on Neural Networks.
6. Bhattacharyya, C., & Keerthi, S. S. (2000). Information geometry and plefka's mean-field theory. J. Phys. A: Math. Gen., 55(7), 1307-1312.
7. Bishop, M. C., Lawrence, N., Jaakkola, T., & Jordan, M. I. (1997). Approximating posterior distributions in belief networks using mixtures. In Jordan, M. I., Kearns, M. J., & Solla, S. (Eds.), Advances in Neural Information Processing Systems 10. MIT press.
8. Geman, S., & Geman, D. (1984). Stochastic relaxation,gibbs distribution,and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 721-741.
9. Haft, M., Hofmann, R., & Tresp, V. (1999). Model independent mean-field theory as a local method for approximate propagation of information. Network: Computation in Neural Systems, 10(1), 93-105.
10. Hinton, G. E., Dayan, P., Frey, B., & Neal, R. (1995). The wake sleep algorithm for unsupervised neural networks. Science, 268, 1158-1161.
11. Horvitz, E. J., Suermondt, H. J., & Cooper, G. (1989). Bounded conditioning: Flexible inference for decisions under scarce resources. In Conference on Uncertainity in Artificial Intelligence: Proceedings of the fifth conference. Mountain View, CA: Assosciation for UAI.
12. Jaakkola, T., & Jordan, M. I. (1999). Variational probabilistic inference and the qmr-dt database. Journal of Artificial Intelligence Research, 10, 291-322.
13. Jensen, C., Kong, A., & Kjaerulff, U. (1995). Blocking gibbs sampling in very large probabilistic expert systems. In International Journal of Human Computer Studies. Special issue on Real World Applications of Uncertain Reasoning.
14. Jordan, M. I., Ghahramani, Z., Jaakkola, S. T., & Saul, L. (1997). An introduction to variational methods for graphical models. In Jordan, M. I. (Ed.), Learning in Graphical models.
15. Kappen, H. J., & Rodriguez, F. B. (1998). Boltzmann machine learning using mean field theory and linear response correction. In Jordan, M. I., Kearns, M. J., & Solla, S. A. (Eds.), Advances in Neural Information Processing Systems 10. MIT press.
16. Kearns, M., & Saul, L. (1998). Large deviation methods for approximate probabilistic inference with rates of convergence. In Proceedings of the fourteenth Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann.
17. Kjaerulff, U. (1998). Reduction of computational complexity in bayesian networksthrough removal of weak dependences. In Uncertainity and Artificial Intelligence: Proceedings of the Tenth Conference. San Mateo, CA: Morgan Kaufmann.
18. Lauritzen, S., & Spiegelhalter, D. (1988). Local computations with probabilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society B, 50, 157-224.
19. Neal, R. (1992). Connectionist learning of belief networks. Artificial Intelligence, 56, 71-118.
20. Parisi, G. (1988). Statistical Field Theory. Addison-Wesley, Redwood city, CA.
21. Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems. Morgan Kaufmann, San Mateo, CA.
22. Peterson, C., & Anderson, J. R. (1987). A mean field theory learning algorithm for neural networks. Complex Systems, 1, 995-1019.
23. Plefka, T. (1982). Convergence condition of the tap equation for the infinite-ranged ising glass model. J. Phys. A: Math. Gen., 15(6), 1971-1978.
24. Rockafeller, R. T. (1972). Convex Analysis (first edition). Princeton university press.
25. Saul, L., & Jordan, M. I. (1996). Exploiting tractable substructures in intractable networks. In Touretzky, D. S., Mozer, M. C., & Hasselmo, M. E. (Eds.), Advances in Neural Information Processing Systems 8. MIT press.
26. Saul, L., & Jordan, M. I. (1999). Attractor dynamics in feedforward networks. Neural Computation. In press.
27. Saul, L. K., Jaakkola, T., & Jordan, M. I. (1996). Mean field theory for sigmoid belief networks. Journal of Artificial Intelligence Research, 4, 61-76.
28. Shwe, M. A., & Others (1991). Probabilistic diagnosis using a reformulation of the internist-1/qmr knowledge base. Meth. Inform. Med., 30.