Abstract
Deep belief neural network represents many-layered perceptron and permits to overcome some limitations of conventional multilayer perceptron due to deep architecture. The supervised training algorithm is not effective for deep belief neural network and therefore in many studies was proposed new learning procedure for deep neural networks. It consists of two stages. The first one is unsupervised learning using layer by layer approach, which is intended for initialization of parameters (pre-training of deep belief neural network). The second is supervised training in order to provide fine tuning of whole neural network. In this work we propose the training approach for restricted Boltzmann machine, which is based on minimization of reconstruction square error. The main contribution of this paper is new interpretation of training rules for restricted Boltzmann machine. It is shown that traditional approach for restricted Boltzmann machine training is particular case of proposed technique. We demonstrate the efficiency of proposed approach using deep nonlinear auto-encoder.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Computation 18, 1527–1554 (2006)
Hinton, G.: Training products of experts by minimizing contrastive divergence. Neural Computation 14, 1771–1800 (2002)
Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Hinton, G.E.: A practical guide to training restricted Boltzmann machines (Tech. Rep. 2010–000). Machine Learning Group, University of Toronto, Toronto (2010)
Bengio, Y.: Learning deep architectures for AI. Foundations and Trends in Machine Learning 2(1), 1–127 (2009)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Schölkopf, B., Platt, J.C., Hoffman, T. (eds.) Advances in Neural Information Processing Systems, vol. 11, pp. 153–160. MIT Press, Cambridge (2007)
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.-A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research 11, 625–660 (2010)
Golovko, V., Vaitsekhovich, H., Apanel, E., Mastykin, A.: Neural network model for transient ischemic attacks diagnostics. Optical Memory and Neural Networks (Information Optics) 21(3), 166–176 (2012)
Scholz, M., Fraunholz, M., Selbig, J.: Nonlinear principal component analysis: neural network models and applications. In: Principal Manifolds for Data Visualization and Dimension Reduction, pp. 44–67. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Golovko, V., Kroshchanka, A., Rubanau, U., Jankowski, S. (2014). A Learning Technique for Deep Belief Neural Networks. In: Golovko, V., Imada, A. (eds) Neural Networks and Artificial Intelligence. ICNNAI 2014. Communications in Computer and Information Science, vol 440. Springer, Cham. https://doi.org/10.1007/978-3-319-08201-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-08201-1_13
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08200-4
Online ISBN: 978-3-319-08201-1
eBook Packages: Computer ScienceComputer Science (R0)