Efficient Learning in Boltzmann Machines Using Linear Response Theory

Neural Computation

Volumn 10, Issue 5, 1998, Pages 1137-1156

  Kappen, H J ^a   Rodriguez F B ^b  

^a RADBOUD UNIVERSITY NIJMEGEN   (Netherlands)

^b UNIVERSIDAD AUTÓNOMA DE MADRID   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0001000562     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976698300017386     Document Type: Article

References (26)

1. Ackley, D., Hinton, G., & Sejnowski, T. (1985). A learning algorithm for Boltzmann machines. Cognitive Science, 9, 147-169.
2. Dayan, P., Hinton, G., Neal, R., & Zemel, R. (1995). The Helmholtz machine. Neural Computation, 7, 889-904.
3. Durbin, R., & Willshaw, D. (1987). An analogue approach to the travelling salesman problem using an elastic net method. Nature, 326, 689-691.
4. Fischer, K., & Hertz, J. (1991). Spin glasses. Cambridge: Cambridge University Press.
5. Galland, C. (1993). The limitations of deterministic Boltzmann machine learning. Network, 4, 355-380.
6. Ginzburg, I., & Sompolinsky, H. (1994). Theory of correlations in stochastic neural networks. Physical Review E, 50, 3171-3191.
7. Hertz, J., Krogh, A., & Palmer, R. (1991). Introduction to the theory of neural computation. Redwood City, CA: Addison-Wesley.
8. Hinton, G. (1989). Deterministic Boltzmann learning performs steepest descent in weight-space. Neural Computation, 1, 143-150.
9. Hopfield, J., & Tank, D. (1985). Neural computation of decision in optimization problems. Biological Cybernetics, 52, 141-152.
10. Itzykson, C., & Drouffe, J.-M. (1989). Statistical field theory. Cambridge: Cambridge University Press.
11. Jaakkola, T., & Jordan, M. (1996). Recursive algorithms for approximating probabilities in graphical models. (MIT Computational Cognitive Science Tech. Rep. No. 9604). Cambridge, MA: MIT.
12. Kappen, H. (1995). Deterministic learning rules for Boltzmann machines. Neural Networks, 8, 537-548.
13. Kappen, H. (1997). Stimulus dependent correlations in stochastic networks. Physical Review E, 55, 5849-5858.
14. Kosowsky, J., & Yuille, A. (1994). The invisible hand algorithm: Solving the assignment problem with statistical physics. Neural Networks, 3, 477-490.
15. Kullback, S. (1959). Information theory and statistics. New York: Wiley.
16. Onsager, L. (1936). Electric moments of molecules in liquids. Journal of the American Chemical Society, 58, 1486-1493.
17. Parisi, G. (1988). Statistical field theory. Reading, MA: Addison-Wesley.
18. Peterson, C., & Anderson, J. (1987). A mean field theory learning algorithm for neural networks. Complex Systems, 1, 995-1019.
19. Plefka, T. (1982). Convergence condition of the TAP equation for the infinite-range Ising spin glass model. Journal of Physics A, 24, 2173.
20. Saul, L., Jaakkola, T., & Jordan, M. (1996). Mean field theory for sigmoid belief networks. Journal of Artificial Intelligence Research, 4, 61-76.
21. Saul, L., & Jordan, M. (1994). Learning in Boltzmann trees. Neural Computation, 6, 1174-1184.
22. Sinclair, A. (1993). Algorithms for random generation and counting: A Markov chain approach. Basel: Birkhäuser.
23. Thouless, D., Anderson, P., & Palmer, R. (1977). Solution of "solvable model of a spin glass." Philosophical Magazine, 35, 593-601.
24. Young, A. (1983). Direct determination of the probability distribution for the spin-glass order parameter. Physical Review Letters, 51, 1206-1209.
25. Yuille, A., Geiger, D., & Bülthoff, H. (1991). Stereo integration, mean field theory and psychophysics. Network, 2, 423-442.
26. Yuille, A., & Kosowsky, J. (1994). Statistical physics algorithms that converge. Neural Computation, 6, 341-356.