Abstract
A deep Boltzmann machine (DBM) is a recently introduced Markov random field model that has multiple layers of hidden units. It has been shown empirically that it is difficult to train a DBM with approximate maximum- likelihood learning using the stochastic gradient unlike its simpler special case, restricted Boltzmann machine (RBM). In this paper, we propose a novel pretraining algorithm that consists of two stages; obtaining approximate posterior distributions over hidden units from a simpler model and maximizing the variational lower-bound given the fixed hidden posterior distributions. We show empirically that the proposed method overcomes the difficulty in training DBMs from randomly initialized parameters and results in a better, or comparable, generative model when compared to the conventional pretraining algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bengio, Y., Courville, A., Vincent, P.: Representation Learning: A Review and New Perspectives. arXiv:1206.5538 [cs.LG] (June 2012)
Bishop, C.M.: Pattern Recognition and Machine Learning, corrected 2nd printing edn. Springer (2007)
Cho, K.: Improved Learning Algorithms for Restricted Boltzmann Machines. Master’s thesis, Aalto University School of Science (2011)
Desjardins, G., Courville, A., Bengio, Y.: On training deep Boltzmann machines. arXiv:1203.4416 [cs.NE] (March 2012)
Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Hinton, G.: Training products of experts by minimizing contrastive divergence. Neural Computation 14, 1771–1800 (2002)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE (11), 2278–2324
Marlin, B.M., Swersky, K., Chen, B., de Freitas, N.: Inductive principles for restricted Boltzmann machine learning. In: Proc. of the 13th Int. Conf. on Artificial Intelligence and Statistics (AISTATS 2010), pp. 509–516 (2010)
Montavon, G., Müller, K.-R.: Deep Boltzmann machines and the centering trick. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) NN: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 621–637. Springer, Heidelberg (2012)
Raiko, T., Valpola, H., LeCun, Y.: Deep learning made easier by linear transformations in perceptrons. In: Proc. of the 15th Int. Conf. on Artificial Intelligence and Statistics (AISTATS 2012), La Palma, Canary Islands, Spain (April 2012)
Salakhutdinov, R., Hinton, G.E.: A Better Way to Pre-Train Deep Boltzmann Machines. In: Advances in Neural Information Processing Systems (2012)
Salakhutdinov, R.: Learning deep Boltzmann machines using adaptive MCMC. In: Fürnkranz, J., Joachims, T. (eds.) Proc. of the 27th Int. Conf. on Machine Learning (ICML 2010), pp. 943–950. Omnipress, Haifa (2010)
Salakhutdinov, R., Hinton, G.: An efficient learning procedure for deep Boltzmann machines. Tech. Rep. MIT-CSAIL-TR-2010-037, MIT (August 2010)
Salakhutdinov, R., Hinton, G.E.: Deep Boltzmann machines. In: Proc. of the Int. Conf. on Artificial Intelligence and Statistics (AISTATS 2009), pp. 448–455 (2009)
Tieleman, T., Hinton, G.E.: Using fast weights to improve persistent contrastive divergence. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, pp. 1033–1040. ACM, New York (2009)
Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11, 3371–3408 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cho, K., Raiko, T., Ilin, A., Karhunen, J. (2013). A Two-Stage Pretraining Algorithm for Deep Boltzmann Machines. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds) Artificial Neural Networks and Machine Learning – ICANN 2013. ICANN 2013. Lecture Notes in Computer Science, vol 8131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40728-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-40728-4_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40727-7
Online ISBN: 978-3-642-40728-4
eBook Packages: Computer ScienceComputer Science (R0)