Abstract
Artificial neural networks (ANNs) typified by deep learning (DL) is one of the artificial intelligence technology which is attracting the most attention of researchers recently. However, the learning algorithm used in DL is usually with the famous error-backpropagation (BP) method. In this paper, we adopt a reinforcement learning (RL) algorithm “Stochastic Gradient Ascent (SGA)” proposed by Kimura and Kobayashi into a Deep Belief Net (DBN) with multiple restricted Boltzmann machines (RBMs) instead of BP learning method. A long-term prediction experiment, which used a benchmark of time series forecasting competition, was performed to verify the effectiveness of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Box, G.E.P., Pierce, D.A.: Distribution of residual autocorrelations in autoregressive-integrated moving average time series models. J. Am. Stat. Ass. 65(332), 1509–1526 (1970)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representation by back-propagating errors. Nature 232(9), 533–536 (1986)
Casdagli, M.: Nonlinear prediction of chaotic time series. Phys. D 35, 335–356 (1981)
Lendasse, A., Oja, E., Simula, O., Verleysen, M.: Time series prediction competition: the CATS benchmark. In: Proceedings of International Joint Conference on Neural Networks (IJCNN 2004), pp. 1615–1620 (2004)
Lendasse, A., Oja, E., Simula, O., Verleysen, M.: Time series prediction competition: the CATS benchmark. Neurocomputing 70, 2325–2329 (2007)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)
Kuremoto, T., Obayashi, M., Kobayashi, M.: Neural forecasting systems. In: Weber, C., Elshaw, M., Mayer, N.M. (eds.) Reinforcement Learning, Theory and Applications, Chap. 1, pp. 1–20. INTECH (2008)
Kuremoto, T., Kimura, S., Kobayashi, K., Obayashi, M.: Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing 137(5), 47–56 (2014)
Kuremoto, T., Hirata, T., Obayashi, M., Mabu, S., Kobayashi, K.: Forecast chaotic time series data by DBNs. In: Proceedings of the 7th International Congress on Image and Signal Processing (CISP 2014), pp. 1304–1309, October 2014
Hirata, T., Kuremoto, T., Obayashi, M., Mabu, S.: Time series prediction using DBN and ARIMA. In: International Conference on Computer Application Technologies (CCATS 2015). Matsue, Japan, pp. 24–29, September 2015
Zhang, G.P.: Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50, 159–175 (2003)
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012)
Kimura, H., Kobayashi, S.: Reinforcement learning for continuous action using stochastic gradient ascent. In: Proceedings of 5th Intelligent Autonomous Systems, pp. 288–295 (1998)
Acknowledgment
This work was supported by JSPS KAKENHI Grant No. 26330254 and No. 25330287.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Hirata, T., Kuremoto, T., Obayashi, M., Mabu, S., Kobayashi, K. (2016). Deep Belief Network Using Reinforcement Learning and Its Applications to Time Series Forecasting. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9949. Springer, Cham. https://doi.org/10.1007/978-3-319-46675-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-46675-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46674-3
Online ISBN: 978-3-319-46675-0
eBook Packages: Computer ScienceComputer Science (R0)