Abstract
In this paper, we proposed a framework to train Restricted Boltzmann Machine (RBM) which is the basic block for Deep Belief Network (DBN). By introducing sparsity constraint to the Contrastive Divergence algorithm (CD algorithm), we trained RBMs with better performance than the off-the-shelf model in MNIST handwritten digit data set. The sparse model suffer from saturation slightly, however, by using a trade-off coefficient, the saturation problem can be solved well. To our knowledge, the sparsity constraint was first introduced to the hidden units of RBM.
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
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Technical report, DTIC Document (1985)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Lee, H., Ekanadham, C., Ng, A.: Sparse deep belief net model for visual area v2. In: Advances in Neural Information Processing Systems, vol. 20, pp. 873–880 (2008)
Le, Q., Monga, R., Devin, M., Corrado, G., Chen, K., Ranzato, M., Dean, J., Ng, A.: Building high-level features using large scale unsupervised learning. arXiv preprint arXiv:1112.6209 (2011)
Osadchy, M., Cun, Y., Miller, M.: Synergistic face detection and pose estimation with energy-based models. The Journal of Machine Learning Research 8, 1197–1215 (2007)
Seide, F., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: Proc. Interspeech, pp. 437–440 (2011)
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Processing Magazine (2012)
Lee, H., Largman, Y., Pham, P., Ng, A.: Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in Neural Information Processing Systems, vol. 22, pp. 1096–1104 (2009)
Hamel, P., Eck, D.: Learning features from music audio with deep belief networks. In: 11th International Society for Music Information Retrieval Conference, ISMIR 2010 (2010)
Hinton, G., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)
Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Chappell, M., Humphreys, M.S.: An auto-associative neural network for sparse representations: Analysis and application to models of recognition and cued recall. Psychological Review 101(1), 103 (1994)
Bengio, Y.: Learning deep architectures for ai. Foundations and Trends® in Machine Learning 2(1), 1–127 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hu, Z., Hu, W., Zhang, C. (2014). Training Deep Belief Network with Sparse Hidden Units. In: Li, S., Liu, C., Wang, Y. (eds) Pattern Recognition. CCPR 2014. Communications in Computer and Information Science, vol 483. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-45646-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-662-45646-0_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-45645-3
Online ISBN: 978-3-662-45646-0
eBook Packages: Computer ScienceComputer Science (R0)