Abstract
Background
Based on restricted Boltzmann machine (RBM), the deep learning models can be roughly divided into deep belief networks (DBNs) and deep Boltzmann machine (DBM). However, the overfitting problems commonly exist in neural networks and RBM models. In order to alleviate the overfitting problem, lots of research has been done. This paper alleviated the overfitting problem in RBM and proposed the weight uncertainty semi-restricted Boltzmann machine (WSRBM) to improve the ability of image recognition and image reconstruction.
Methods
First, this paper built weight uncertainty RBM model based on maximum likelihood estimation. And in the experimental section, this paper verified the effectiveness of the weight uncertainty deep belief network and the weight uncertainty deep Boltzmann machine. Second, in order to obtain better reconstructed images, this paper used the semi-restricted Boltzmann machine (SRBM) as the feature extractor and built the WSRBM. Lastly, this paper used hybrid Monte Carlo sampling and cRBM to improve the classification ability of WSDBM.
Results
The experiments showed that the weight uncertainty RBM, weight uncertainty DBN and weight uncertainty DBM were effective compared with the dropout method. And the WSDBM model performed well in image recognition and image reconstruction as well.
Conclusions
This paper introduced the weight uncertainty method to RBM, and proposed a WSDBM model, which was effective in image recognition and image reconstruction.
Similar content being viewed by others
References
Erhan D, Vincent P, Bengio Y. Why does unsupervised pre-training help deep learning. J Mach Learn Res. 2010;11(3):625–60.
Hinton G. Training products of experts by minimizing contrastive divergence. Neural Comput. 2002;14(8):1771–800.
Roux N, Bengio Y. Representational power of restricted Boltzmann machines and deep belief networks. Neural Comput. 2008;20(6):1631–49.
Hinton G, Osindero S, Teh Y. A fast learning algorithm for deep belief nets. Neural Comput. 2006;18(7):1527–54.
Hinton G, Salakhutdinov R. Reducing the dimensionality of data with neural networks. Science. 2006;313(5786):504–7.
Lee H, Pham P, Yan L, et al. Unsupervised feature learning for audio classification using convolutional deep belief networks. Adv Neural Inf Process Syst. 2009;22:1096–1104.
Norouzi M, Ranjbar M, Mori G. Stacks of convolutional restricted Boltzmann machines for shift-invariant feature learning. IEEE Conf Comput Vis Pattern Recognit. 2009;1–4:2735–2742.
Salakhutdinov R, Larochelle H. Efficient learning of deep Boltzmann machines. J Mach Learn Res. 2010;9(8):693–700.
Salakhutdinov R, Hinton G. An efficient learning procedure for deep Boltzmann machines. Neural Comput. 2012;24(8):1967–2006.
Bengio Y, Boulanger-Lewandowski N, Pascanu R. Advances in optimizing recurrent networks. IEEE International Conference on Acoustics, 2012: 8624–8628.
Zhang J, Ding S, Zhang N, et al. Incremental extreme learning machine based on deep feature embedded. Int J Mach Learn Cybernet. 2016;7(1):111–20.
Zhang N, Ding S, Shi Z. Denoising Laplacian multi-layer extreme learning machine. Neurocomputing. 2016;171:1066–74.
Ding S, Zhang N, Xu X, et al. Deep Extreme learning machine and its application in EEG classification. Math Probl Eng. 2015;2015:1–11.
Li J, Li X, Yang B, et al. Segmentation-based image copy-move forgery detection scheme. IEEE Trans Inf Forensics Secur. 2015;10(3):507–18.
Zheng Y, Jeon B, Xu D, et al. Image segmentation by generalized hierarchical fuzzy C-means algorithm. J Intell Fuzzy Syst. 2015;28(2):961–73.
Gu B, Sheng V, Tay K, et al. Incremental support vector learning for ordinal regression. IEEE Trans Neural Netw Learn Syst. 2015;26(7):1403–16.
Srivastava N, Hinton G, Krizhevsky A. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929–58.
Blundell C, Cornebise J, Kavukcuoglu K. Weight uncertainty in neural networks. International Conference on Machine Learning, France, 2015.
Osindero S, Hinton G. Modeling image patches with a directed hierarchy of markov random fields. Adv Neural Inf Process Syst. 2008;20:1121–1128.
Lee T, Yoon S. Boosted categorical restricted Boltzmann machine for computational prediction of splice junctions. International Conference on Machine Learning, France, 2015.
Hinton G. A practical guide to training restricted Boltzmann machines. Momentum. 2010;9(1):926.
Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. Technical report U. Toronto, 2009.
Salakhutdinov R. Learning and evaluating Boltzmann machines, Technical Report U. Toronto, 2008
Neal R. Connectionist learning of belief networks. Artif Intell. 1992;56(92):71–113.
Kirkpatrick S, Jr G, Vecchi M. Optimization by simulated annealing. Science. 1983;220(4598):671–80.
Salakhutdinov R. Learning in Markov random fields using tempered transitions. Adv Neural Inf Process Syst. 2009;22:1598–1606.
Desjardins G, Courville A, Bengio Y, et al. Tempered markov chain monte carlo for training of restricted Boltzmann machines. International Conference on Artificial Intelligence and Statistics, Italy, 2010: 145–152.
Tieleman T. Training restricted Boltzmann machines using approximations to the likelihood gradient. International Conference on Machine Learning, Finland, 2008: 1064–1071.
Tieleman T, Hinton G. Using fast weights to improve persistent contrastive divergence. International Conference on Machine Learning, Canada, 2009: 1033–1040.
Jordan M, Ghahramani Z, Jaakkola T, et al. An introduction to variational methods for graphical models. Mach Learn. 1999;37(2):183–233.
Ackley H, Hinton G, Sejnowski J, et al. a mean field theory learning algorithm for neural network. Complex Syst. 1987;1:995–1019.
Hinton G, Salakhutdinov R. A better way to pretrain deep Boltzmann machines. Adv Neural Inf Process Syst. 2012;3:2447–2455.
Ranzato M, Krizhevsky A, Hinton G. Factored 3-way restricted Boltzmann machines for modeling natural images. J Mach Learn Res. 2010;9:621–8.
Acknowledgments
This work is supported by the National Natural Science Foundation of China (No. 61379101), the National Natural Science Foundation of China (No. 61672522), the National Key Basic Research Program of China (No. 2013CB329502), the Priority Academic Program Development of Jiangsu Higer Education Institutions and the Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
Jian Zhang, Shifei Ding, Nan Zhang and Yu Xue declare that they have no conflict of interest.
Informed Consent
Informed consent was not required as no human or animals were involved.
Human and Animal Rights
This article does not contain any studies with human or animal subjects performed by any of the authors.
Rights and permissions
About this article
Cite this article
Zhang, J., Ding, S., Zhang, N. et al. Weight Uncertainty in Boltzmann Machine. Cogn Comput 8, 1064–1073 (2016). https://doi.org/10.1007/s12559-016-9429-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-016-9429-1