Deep learning has proven to be beneficial for complex tasks such as classifying the image, pattern recognition, speech recognition, natural language processing, and recommendation systems. Autoencoder, Restricted Boltzmann Machine, Deep belief Network and Convolutional Neural network are four different types of architecture used in deep learning. Deep Belief Network is now the new the state of the art for many fields of machine learning research. The main aim of this survey is to widely cover deep belief network architecture and their practical applications such as computer-aided diagnosis for the dreadful diseases, pattern recognition and also in the field of industry. The proposed work helps to improve the classification performance for breast cancer to a certain extent, which provides a good direction for the future classification of breast cancer. At last, the limitations of Deep Belief network and list of future research information has been given.

deep learning, autoencoder, restricted Boltzmann machine, deep belief network, convolutional neural network.

[1] A.M. Abdel-Zaher, and A.M. Eldeib, “Breast cancer classification using deep belief networks”, Expert Systems with Applications, 46, 2016, pp.139-144.
[2] G.E. Hinton, “A practical guide to training restricted Boltzmann machines”. In Neural networks: Tricks of the trade, Springer, Berlin, Heidelberg, 2012, pp.599-619.
[3] G.E. Hinton, S. Osindero, and Y.W. Teh, “A fast learning algorithm for deep belief nets”, Neural computation, 18(7), 2006, pp.1527-1554.
[4] D. Maltoni, D.Maio, A.K. Jain, and S. Prabhakar, “Handbook of fingerprint recognition”, Springer Science & Business Media, 2009.
[5] S. Kim, B. Park, B.S. Song, and S. Yang, “Deep belief network based statistical feature learning for fingerprint liveness detection”, Pattern Recognition Letters, 77, 2016, pp.58-65.
[6] J. Hua, andZ. Huaxiang, “Analysis on the content features and their correlation of web pages for spam detection”, China Communications, 12(3), 2015, pp.84-94.
[7] W. Wang, G. Zeng, and D. Tang, “Using evidence based content trust model for spam detection”,Expert Systems with Applications, 37(8), 2010, pp.5599-5606.
[8] YuanchengLi, Xiangqian Nie, and RongHuang, “Web spam classification method based on deep belief networks”, Expert Systems with Applications, 96, 2018, pp.261-270.
[9] A. Dedinec, S. Filiposka, A. Dedinec, and L. Kocarev, “Deep belief network based electricity load forecasting: An analysis of Macedonian case”, Energy, 115, 2016, pp.1688-1700.
[10] J. Sun, R. Wyss, A. Steinecker, and P. Glocker, “Automated fault detection using deep belief networks for the quality inspection of electromotors”, Tm-TechnischesMessen, 81(5), 2014, pp.255-263.
[11] J. Sun, A. Steinecker, and P. Glocker, “Application of deep belief networks for precision mechanism quality inspection”, In International Precision Assembly Seminar,Springer, Berlin, Heidelberg, 2014, pp. 87-93.
[12] X.Q. Liu, H.Y. Zhang, J. Liu,and J. Yang, “Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network”, IEEE transactions on industrial electronics, 47(5),2000, pp.1021-1030.
[13] J. McBain, and M. Timusk, “Feature extraction for novelty detection as applied to fault detection in machinery”, Pattern Recognition Letters, 32(7), 2011, pp.1054-1061.
[14] F. Paulin, and A. Santhakumaran, “Classification of breast cancer by comparing back propagation training algorithms”, International Journal on Computer Science and Engineering, 3(1), 2011, pp.327-332.
[15] G. Wang, J. Qiao, X. Li, L. Wang, andX. Qian, “Improved classification with semi-supervised deep belief network”, IFAC-PapersOnLine, 50(1), 2017, pp.4174-4179.
[16] M.S.S. Rao, S.A. Soman, B.L. Menezes, P. Chawande, P. Dipti, and T. Ghanshyam, “An expert system approach to short-term load forecasting for Reliance Energy Limited, Mumbai”, In Power India Conference, 2006 IEEE, (pp. 6-pp). IEEE.
[17] R. Hrasko, A.G. Pacheco, and R.A. Krohling, “Time series prediction using restricted boltzmann machines and backpropagation”, Procedia Computer Science, 55, 2015, pp.990-999.
[18] H. Li, X. Li, M. Ramanathan, and A. Zhang, “Identifying informative risk factors and predicting bone disease progression via deep belief networks”, Methods, 69(3), 2014, pp.257-265.
[19] W. Liu, Z. Wang, X. Liu, N. Zeng, Y. Liu, and F.E. Alsaadi, “A survey of deep neural network architectures and their applications”, Neurocomputing, 234,2017, pp.11-26.
[20] G.E. Hinton, “Training products of experts by minimizing contrastive divergence”, Neural computation, 14(8), 2002, pp.1771-1800.
[21] A. Tang, K. Lu, Y. Wang, J. Huang, and H. Li, “A real-time hand posture recognition system using deep neural networks”, ACM Transactions on Intelligent Systems and Technology (TIST), 6(2), 2015, p.21.
[22] V. Lokare, S. Birari, O. Patil, “Application of Deep belief networks for image compression”, International journal of computer science and information technologies, vol.6(5), 2015, 4799-4803.