Abstract
This article proposes an efficient method for Restricted Boltzmann Machine (RBM) to learn sparse feature. Deep learning algorithms are used more and more often. The Deep Belief Network (DBN) model, which is composed of RBM, is considered as one of the most effective deep learning algorithms. RBM or auto-encoder (AE) is the basic model to build deep networks. However, RBM may produce redundant features without any constraints, then much improved RBM were proposed by added a regularization term to control sparsity of hidden units. Most of the proposed algorithms need a parameter to control the sparseness of the code. In this paper, we proposed a multiobjective optimization model to avoid user-defined constant that is a trade-off between the regularization term and the reconstruction error based on SR-RBM. We employ evolutionary algorithm to optimize the distortion function and the sparsity of hidden units simultaneously. Experimental results show that our novel approach can learn useful sparse feature without a user-define constant and it performs better than other feature learning models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Felleman, D.J.: Distributed hierarchical processing in the primate cerebral cortex. Cereb. Cortex 1(1), 1–47 (1991)
Lee, T.S.: Hierarchical Bayesian inference in the visual cortex. Opt. Soc. Am. A, Opt. Image Sci. Vis. 20(7), 1434–1448 (2003)
Morris, G.: Anatomical funneling, sparse connectivity and redundancy reduction in the neural networks of the basal ganglia. Physiol.-Paris 97(4–6), 581–589 (2003)
Kruger, N.: Deep hierarchies in the primate visual cortex: What can we learn for computer vision? IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1847–1871 (2013)
Arel, I.: Deep machine learning—A new frontier in artificial intelligence research [research frontier]. IEEE Comput. Intell. Mag. 5(4), 13–18 (2010)
Hou, W.: Blind image quality assessment via deep learning. IEEE Trans. Neural Netw. Learn. Syst. 26(6), 1275–1286 (2015)
Silver, D.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484–489 (2015)
Xu, Y.: A regression approach to speech enhancement based on deep neural networks. IEEE/ACM Trans. Audio Speech Lang. Process. 23(1), 7–19 (2015)
Krizhevsky, A., Sutskever, I.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates Inc. (2012)
Karpathy, A., Toderici, G.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference Computer Vision and Pattern Recognition, pp. 1725–1732. IEEE (2014)
Sainath, T.N.: Deep convolutional neural networks for large-scale speech tasks. Neural Netw. 64, 39–48 (2015)
Hinton, G.E., Sejnowski, T.J.: Learning and relearning in Boltzmann machines. In: Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. MIT Press, pp. 45–76 (1986)
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). doi:10.1007/978-3-642-33275-3_2
Makhzani, A., Frey, B.: K-sparse autoencoders. Comput. Sci. (2013)
Rolfe, J.T.: Discriminative recurrent sparse auto-encoders. Comput. Sci. (2013)
Ranzato, M.: Sparse feature learning for deep belief networks. In: Proceedings of Advances in Neural Information Processing Systems, Vancouver, BC, Canada, pp. 1185–1192December (2007)
Lee, H.: Sparse deep belief net model for visual area V2. Adv. Neural. Inf. Process. Syst. 20, 873–880 (2007)
Ji, N.-N.: A sparse-response deep belief network based on rate distortion theory. Pattern Recognit. 47(9), 3179–3191 (2014)
Luo, H.: Sparse Group Restricted Boltzmann Machines. Statistics (2010)
Keyvanrad, M.A., Homayounpour, M.M.: Normal sparse deep belief network. In: International Joint Conference on Neural Networks, pp. 1–7 (2015)
Olshausen, B.A.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583), 607–609 (1996)
Li, L.: An evolutionary multiobjective approach to sparse reconstruction. IEEE Trans. Evol. Comput. 8(16), 827–845 (2014)
Chen, W.: Response surface and multiobjective optimization methodology for the design of compliant interconnects. IEEE Trans. Compon. Packag. Manuf. Technol. 4(11), 1769–1777 (2014)
Garcia-Piquer, A.: Large-scale experimental evaluation of cluster representations for multiobjective evolutionary clustering. IEEE Trans. Evol. Comput. 18(1), 36–53 (2014)
Svenson, J., Santner, T.: Multiobjective Optimization of Expensive-to-Evaluate Deterministic Computer Simulator Models. Elsevier Science Publishers B. V, Amsterdam (2016)
Asrari, A.: Pareto dominance-based multiobjective optimization method for distribution network reconfiguration. IEEE Trans. Smart Grid 7(3), 1401–1410 (2016)
Csirmaz, L.: Using multiobjective optimization to map the entropy region. Comput. Optim. Appl. 1, 1–23 (2016)
Branke, J.: Interactive evolutionary multiobjective optimization driven by robust ordinal regression. Bull. Pol. Acad. Sci. Tech. Sci. 58(3), 347–358 (2016)
Gong, M.: A multiobjective sparse feature learning model for deep neural networks. IEEE Trans. Neural Netw. Learn. Syst. 26(12), 3263–3277 (2015)
Li, Y.: Dynamic-context cooperative quantum-behaved particle swarm optimization based on multilevel thresholding applied to medical image segmentation. Inf. Sci. 294, 408–422 (2015)
Cover, T.M.: Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing). Wiley, Hoboken (2006)
Zhang, Q.: MOEA/D: a multiobjective evolutionary algorithm based on decomposition. IEEE Trans. Evol. Comput. 11(6), 712–731 (2008)
Hillermeier, C.: Nonlinear Multiobjective Optimization. Birkhaüser Verlag, Basel (2001)
Venske, S.M.S., Gonçalves, R.A.: ADEMO/D: adaptive differential evolution for multiobjective problems. In: Brazilian Symposium on Neural Networks, pp. 226–231. IEEE (2012)
Rachmawati, L.: Multiobjective evolutionary algorithm with controllable focus on the knees of the Pareto front. IEEE Trans. Evol. Comput. 13(4), 810–824 (2009)
Vincent, P.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11(12), 3371–3408 (2010)
Davis, G.: Adaptive nonlinear approximations. Ph.D. dissertation, Department of Mathematics Courant Institute Mathematical Science, New York University, New York (1994)
Ng, A.Y.: Feature selection, L1 vs. L2 regularization, and rotational invariance. In: Proceedings of 21st International Conference Machine Learning, Banff, AB, Canada, pp. 379–387 (2004)
Lee, H., Battle, A.: Efficient sparse coding algorithms. In: Proceedings of Advances in Neural Information Processing Systems, Vancouver, BC, Canada, pp. 801–808 (2006)
Qin, A.K., Suganthan, P.N.: Self-adaptive differential evolution algorithm for numerical optimization. In: IEEE Congress on Evolutionary Computation, vol. 2, pp. 1785–1791 (2005)
Branke, J., Deb, K., Dierolf, H., Osswald, M.: Finding knees in multi-objective optimization. In: Yao, X., et al. (eds.) PPSN 2004. LNCS, vol. 3242, pp. 722–731. Springer, Heidelberg (2004). doi:10.1007/978-3-540-30217-9_73
The MNIST Database of Handwirtten Digits. http://yann.lecun.com/exdb/mnist/
Learning Multiple Layers of Reatires from Tiny Images. Alex Krizhevsky (2009). http://www.cs.toronto.edu/~kriz/cifar.html/
Miettinen, K.: Nonlinear Multiobjective Optimization. Kluwer, Norwell (1999)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Li, Y., Bai, X., Liang, X., Jiao, L. (2017). Sparse Restricted Boltzmann Machine Based on Multiobjective Optimization. In: Shi, Y., et al. Simulated Evolution and Learning. SEAL 2017. Lecture Notes in Computer Science(), vol 10593. Springer, Cham. https://doi.org/10.1007/978-3-319-68759-9_73
Download citation
DOI: https://doi.org/10.1007/978-3-319-68759-9_73
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68758-2
Online ISBN: 978-3-319-68759-9
eBook Packages: Computer ScienceComputer Science (R0)