Abstract
In this paper we introduce a methodology for the simple integration of almost-independence information on the visible (input) variables of the restricted Boltzmann machines (RBM) into the weight decay regularization of the contrastive divergence and stochastic gradient descent algorithm. After identifying almost independent clusters of the input coordinates by Chow-Liu tree and forest estimation, the RBM regularization strategy is constructed. We show an example of a sparse two hidden layer Deep Belief Net (DBN) applied on the MNIST data classification problem. The performance is quantified by estimating misclassification rate and measure of manifold disentanglement. Approach is benchmarked to the full model.
This work was developed in Fraunhofer Cluster of Excellence “Cognitive Internet Technologies”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bach, F.R., Jordan, M.I.: Beyond independent components: trees and clusters. J. Mach. Learn. Res. 4, 1205–1233 (2003)
Brahma, P.P., Wu, D., She, Y.: Why deep learning works: a manifold disentanglement perspective. IEEE Trans. Neural Netw. Learn. Syst. 27(10), 1997–2007 (2016). https://doi.org/10.1109/TNNLS.2015.2496947
Chow, C., Liu, C.: Approximating discrete probability distributions with dependence trees. IEEE Trans. Inf. Theory 14, 462–467 (1968)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley Interscience (2006). https://doi.org/10.1002/047174882X
Dasgupta, S.: The Sample Complexity of Learning Fixed-Structure Bayesian Networks. Kluwer Academic Publishers, Boston (1999). https://doi.org/10.1023/A:1007417612269
Fischer, A., Igel, C.: An introduction to restricted Boltzmann machines. In: Alvarez, L., Mejail, M., Gomez, L., Jacobo, J. (eds.) CIARP 2012. LNCS, vol. 7441, pp. 14–36. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33275-3_2
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8) (2002). https://doi.org/10.1162/089976602760128018
Hinton, G.E.: A practical guide to training restricted Boltzmann machines. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 599–619. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_32
Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 27–54 (2006). https://doi.org/10.1162/neco.2006.18.7.1527
Koller, D., Friedman, N.: Probabilistic Graphical Models, Principles and Techniques. MIT Press, Cambridge (2009). https://doi.org/10.1017/S0269888910000275
Koller, D., Friedman, N., Getoor, L., Taskar, B.: Graphical Models in a Nutshell. MIT Press, Cambridge (2007). https://doi.org/10.1.1.146.2935
Meek, C.: Finding a path is harder than finding a tree. J. Artif. Intell. Res. 15 (2001). https://doi.org/10.1613/jair.914
Pinsker, M.S.: On estimation of information via variation. Probl. Inf. Transm. 41(2), 71–75 (2005). https://doi.org/10.1007/s11122-005-0012-8
Salakhutdinov, R., Mnih, A., Hinton, G.E.: Restricted Boltzmann machines for collaborative filtering. In: International Conference on Machine Learning 24 (2007). https://doi.org/10.1145/1273496.1273596
Tan, V.Y.F., Anandkumar, A., Willsky, A.: Learning high-dimensional markov forest distributions: analysis of error rates. J. Mach. Learn. Res. 12, 1617–1653 (2011)
West, D.B.: Introduction to Graph Theory, 2nd edn. Prentice Hall, Upper Saddle River (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sarishvili, A., Wirsen, A., Jirstrand, M. (2019). On Chow-Liu Forest Based Regularization of Deep Belief Networks. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions. ICANN 2019. Lecture Notes in Computer Science(), vol 11731. Springer, Cham. https://doi.org/10.1007/978-3-030-30493-5_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-30493-5_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30492-8
Online ISBN: 978-3-030-30493-5
eBook Packages: Computer ScienceComputer Science (R0)