Abstract
Graphical models are considered more and more as a key technique for describing the dependency relations of random variables. Various learning and inference algorithms have been described and analysed. This article demonstrates how an important subclass of graphical models can be treated by transforming the underlying model into a regular feedforward network with special, yet deterministic, activation functions. Inference and the relevant quantities for learning can be calculated exactly in these networks. Moreover, all the known techniques for feedforward networks can be exploited and applied here.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
G. F. Cooper. The computational complexity of probabilistic inference using Bayesian belief networks. Artificial Intelligence, 42:393–405, 1990.
D. J. C. MacKay. Equivalence of Boltzmann chains and hidden Markov models. Neural Computation, 8(1):178–181, 1996.
M. J. Nijman and H. J. Kappen. Efficient learning in sparsely connected Boltzmann machines. In C. von der Malsburg, W. von Seelen, J. C. Vorbriiggen and B. Sendhoff, editors, Artificial Neural Networks — ICANN 96, pages 41–46. Springer-Verlag, 1996.
W. H. Press, S. A. Teukolsky, W. T. Vetterling and B. P. Flannery. Numerical Recipes in C. Cambridge University Press, 1988.
S. M. Rüger. Stable dynamic parameter adaptation. In D. Touretzky, M. Mozer and M. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 225–231. MIT Press, 1996.
S. M. Rüger. Decimatable boltzmann machines for diagnosis: Efficient learning and inference. In Proceedings of IMACS'97, Berlin (accepted), 1997.
S. M. Rüger. Zur Theorie künstlicher neuronaler Netze. Verlag Harri Deutsch, Thun, Frankfurt/Main, 1997.
L. K. Saul and M. I. Jordan. Boltzmann chains and hidden Markov models. In G. Tesauro, D. S. Touretzky and T. K. Leen, editors, Advances in Neural Information Processing Systems 7, pages 435–442. MIT Press, 1995.
P. Smyth, D. Heckerman and M. I. Jordan. Probabilistic independence networks for hidden Markov probability models. Neural Computation, 9(2), 20–27. 1997.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rüger, S.M. (1997). Making stochastic networks deterministic. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020180
Download citation
DOI: https://doi.org/10.1007/BFb0020180
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive