Abstract
For the dilemma in determining the structure and shortage of supervision in learning process of the deep learning feature extraction algorithm CDBN, this paper proposes a method to improve this situation by adopting KECA to extract features more deeply and effectively and then we take the extracted features as the input of RBF. We use foreign exchange series to conduct the em-pirical study which shows that the accuracy of the KECDBN-RBF model is obviously improved compared to single RBF.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, H., Murray, A.: A continuous restricted Boltzmann machine with a hardware-amenable learning algorithm. In: Artificial Neural Networks, ICANN 2002, p. 134 (2002)
Chen, H., Murray, A.F.: Continuous restricted Boltzmann machine with an implementable training algorithm. IEE Proc. Vis. Image Signal Process. 150(3), 153–158 (2003)
Sahasrabudhe, M., Namboodiri, A.M.: Learning fingerprint orientation fields using continuous restricted Boltzmann machines. In: 2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 351–355. IEEE (2013)
Chen, Y., Lu, L., Li, X.: Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly. J. Geochem. Explor. 140, 56–63 (2014)
Tang, T.B., Murray, A.F.: Adaptive sensor modelling and classification using a continuous restricted Boltzmann machine (CRBM). Neurocomputing 70(7), 1198–1206 (2007)
Hu, Z., Fan, X., Song, Y., et al.: Joint trajectory tracking and recognition based on bi-directional nonlinear learning. Image Vis. Comput. 27(9), 1302–1312 (2009)
Chen, H., Murray, A.F.: Continuous restricted Boltzmann machine with an implementable training algorithm. IEE Proc. Vis. Image Signal Process. 150(3), 153–158 (2003)
Lin, W.-M., Yang, C.-D., Lin, J.-H., Tsay, M.-T.: A fault classification method by RBF neural network with OLS learning procedure. IEEE Trans. Power Deliv. 16, 473–477 (2001)
Mao, K.: RBF neural network center selection based on fisher ratio class separability measure. IEEE Trans. Neural Netw. 13, 1211–1217 (2002)
Er, M.J., Wu, S., Lu, J., Toh, H.L.: Face recognition with radial basis function (RBF) neural networks. IEEE Trans. Neural Netw. 13, 697–710 (2002)
Guillén, A., Rojas, I., González, J., Pomares, H., Herrera, L., Prieto, A.: Using a new clustering algorithm to design RBF networks for functional approximation problem. In: Proceedings of the Learning 2004 International Conference, pp. 19–24 (2004)
Willmott, C.J., Matsuura, K.: Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30(1), 79–82 (2005)
Coyle, E.J., Lin, J.H.: Stack filters and the mean absolute error criterion. IEEE Trans. Acoust. Speech Signal Process. 36(8), 1244–1254 (1988)
Lin, J.H., Sellke, T.M., Coyle, E.J.: Adaptive stack filtering under the mean absolute error criterion. IEEE Trans. Acoust. Speech Signal Process. 38(6), 938–954 (1990)
Yin, L., Astola, J., Neuvo, Y.: Optimal weighted order statistic filters under the mean absolute error criterion. In: 1991 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1991, pp. 2529–2532. IEEE (1991)
Kassam, S.: Quantization based on the mean-absolute-error criterion. IEEE Trans. Commun. 26(2), 267–270 (1978)
Acknowledgement
This work is supported by Guangxi Key Laboratory of Cryptography and Information Security, Grant/Award Number: GCIS201610.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Chen, X., Tian, Y., Wang, X., Wu, X. (2018). RBF Model Based on the KECDBN. In: Xhafa, F., Caballé, S., Barolli, L. (eds) Advances on P2P, Parallel, Grid, Cloud and Internet Computing. 3PGCIC 2017. Lecture Notes on Data Engineering and Communications Technologies, vol 13. Springer, Cham. https://doi.org/10.1007/978-3-319-69835-9_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-69835-9_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-69834-2
Online ISBN: 978-3-319-69835-9
eBook Packages: EngineeringEngineering (R0)