Abstract
Many models are used to solve classification problems in machine learning. The classification restricted Boltzmann machine (ClassRBM) is a type of self-contained network model that is widely used in various classification applications. To implement classification, the ClassRBM updates the model parameters constantly during the training phase in terms of their class labels so that the model parameters learned from the ClassRBM are different from those learned from the conventional restricted Boltzmann machine (RBM), which is trained by unsupervised learning. In this paper, we demonstrate that the reconstruction errors of the ClassRBM are larger than those of the conventional RBM because of the label information. We then propose a classification model of the restricted Boltzmann machine based on these reconstruction errors. The reconstruction errors are used to train the proposed model to improve the classification performance of the ClassRBM. Extensive experiments are carried out to verify the proposed model. The experimental results demonstrate that the proposed model can improve the classification performance of the ClassRBM.
Similar content being viewed by others
References
Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2(1):1–127
Bengio Y, Lamblin P, Popovici D, Larochelle H et al (2007) Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 19:153–160
Blum C, Socha K (2005) Training feed-forward neural networks with ant colony optimization: an application to pattern classification. In: Fifth International Conference on hybrid intelligent systems, 2005. HIS’05, p 6. IEEE
Chen K, Yang L, Yu X, Chi H (1997) A self-generating modular neural network architecture for supervised learning. Neurocomputing 16(1):33–48
Decoste D, Schölkopf B (2002) Training invariant support vector machines. Mach Learn 46(1–3):161–190
Eiamkanitchat N, Theera-Umpon N, Auephanwiriyakul S (2010) Colon tumor microarray classification using neural network with feature selection and rule-based classification. In: Advances in neural network research and applications. Springer, Berlin, pp 363–372
Elfwing S, Uchibe E, Doya K (2015) Expected energy-based restricted Boltzmann machine for classification. Neural Netw 64:29–38
Fischer A, Igel C (2012) An introduction to restricted Boltzmann machines. In: Progress in pattern recognition, image analysis, computer vision, and applications. Springer, Berlin, pp 14–36
Fischer A, Igel C (2014) Training restricted Boltzmann machines: an introduction. Pattern Recogn 47(1):25–39
Freund Y, Haussler D (1992) Unsupervised learning of distributions on binary vectors using two layer networks. In: Advances in neural information processing systems, pp 912–919
Hansen LK, Salamon P (1990) Neural network ensembles. IEEE Trans Pattern Anal Mach Intell 10:993–1001
Hinton GE (2002) Training products of experts by minimizing contrastive divergence. Neural Comput 14(8):1771–1800
Hinton GE (2007) To recognize shapes, first learn to generate images. Prog Brain Res 165:535–547
Hinton GE (2010) A practical guide to training restricted Boltzmann machines. Momentum 9(1):599–619
Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Huang W, Hong H, Bian K, Zhou X, Song G, Xie K (2015) Improving deep neural network ensembles using reconstruction error. In: 2015 International joint conference on neural networks (IJCNN), pp 1–7. IEEE
Huang W, Zhang N, Hu W, Hong H, Song G, Xie K (2014) Dynamic boosting in deep learning using reconstruction error. In: 2014 International joint conference on neural networks (IJCNN), pp 473–480. IEEE
Ji N, Zhang J, Zhang C, Wang L (2014) Discriminative restricted Boltzmann machine for invariant pattern recognition with linear transformations. Pattern Recogn Lett 45:172–180
Ji NN, Zhang JS, Zhang CX (2014) A sparse-response deep belief network based on rate distortion theory. Pattern Recogn 47(9):3179–3191
Koziol JA, Tan EM, Dai L, Ren P, Zhang JY (2014) Restricted Boltzmann machines for classification of hepatocellular carcinoma. Comput Biol J 2014:1–5
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Larochelle H, Bengio Y (2008) Classification using discriminative restricted Boltzmann machines. In: Proceedings of the 25th international conference on Machine learning, pp 536–543. ACM
Larochelle H, Erhan D, Vincent P (2009) Deep learning using robust interdependent codes. In: International conference on artificial intelligence and statistics, pp 312–319
Larochelle H, Mandel M, Pascanu R, Bengio Y (2012) Learning algorithms for the classification restricted Boltzmann machine. J Mach Learn Res 13(1):643–669
Le Cun BB, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1990) Handwritten digit recognition with a back-propagation network. In: Advances in neural information processing systems. Citeseer, pp 396–404
Lei Y, He Z, Zi Y, Hu Q (2006) Mechanical fault diagnosis model based on feature evaluation and neural networks. Xi’an Jiaotong Daxue Xuebao (Journal of Xi’an Jiaotong University) 40(5):558–562
Li Q, Zhang J, Wang Y, Kang K (2014) Credit risk classification using discriminative restricted Boltzmann machines. In: 2014 IEEE 17th International conference on computational science and engineering (CSE), pp 1697–1700. IEEE
Liu Z, Pu J, Huang T, Qiu Y (2013) A novel classification method for palmprint recognition based on reconstruction error and normalized distance. Appl Intell 39(2):307–314
Lu J, Ho DW, Cao J, Kurths J (2011) Exponential synchronization of linearly coupled neural networks with impulsive disturbances. IEEE Trans Neural Netw 22(2):329–336
Lv JC, Tan KK, Yi Z, Huang S (2008) Stability and chaos of a class of learning algorithms for ica neural networks. Neural Process Lett 28(1):35–47
Lv JC, Yi Z, Li Y (2015) Non-divergence of stochastic discrete time algorithms for pca neural networks. IEEE Trans Neural Netw Learn Syst 26(2):394–399
Pang Z, Liu D, Lloyd SR (2007) Classification of obstructive sleep apnea by neural networks. In: Advances in neural networks–ISNN 2007. Springer, Berlin, pp 1299–1308
Papa JP, Rosa GH, Marana AN, Scheirer W, Cox DD (2015) Model selection for discriminative restricted Boltzmann machines through meta-heuristic techniques. J Comput Sci 9:14–18
Salakhutdinov R, Larochelle H (2010) Efficient learning of deep Boltzmann machines. In: International conference on artificial intelligence and statistics, pp 693–700
Salakhutdinov R, Murray I (2008) On the quantitative analysis of deep belief networks. In: Proceedings of the 25th international conference on Machine learning, pp 872–879. ACM
Schmah T, Hinton GE, Zemel RS, Small SL, Strother SC (2008) Generative versus discriminative training of rbms for classification of fmri images. In: Conference on neural information processing systems, Vancouver, British Columbia, Canada, December, pp 1409–1416
Smolensky P (1986) Information processing in dynamical systems: foundations of harmony theory. Technical Report, DTIC Document
Specht DF (1990) Probabilistic neural networks. Neural Netw 3(1):109–118
Tomczak JM, Zieba M (2015) Classification restricted Boltzmann machine for comprehensible credit scoring model. Expert Syst Appl 42(4):1789–1796
Yi Z (2010) Foundations of implementing the competitive layer model by lotka-volterra recurrent neural networks. IEEE Trans Neural Netw 21(3):494–507
Yi Z, Lv JC, Zhang L (2006) Output convergence analysis for a class of delayed recurrent neural networks with time-varying inputs. IEEE Trans Syst Man Cybern Part B Cybern 36(1):87–95
Yu Q, Hou Y, Zhao X, Cheng G (2014) Rényi divergence based generalization for learning of classification restricted Boltzmann machines. In: 2014 IEEE International conference on data mining workshop (ICDMW), pp 692–697. IEEE
Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans Syst Man Cybern Part C Appl Revi 30(4):451–462
Acknowledgements
This work was supported by the National Science Foundation of China (Grant No. 61375065) partially supported by the State Key Program of National Science Foundation of China (Grant Nos. 61432012 and 61432014).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yin, J., Lv, J., Sang, Y. et al. Classification model of restricted Boltzmann machine based on reconstruction error. Neural Comput & Applic 29, 1171–1186 (2018). https://doi.org/10.1007/s00521-016-2628-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2628-6