Abstract
A denoising unit based on wavelet multiresolution analysis is added ahead of the multilayered perceptron with global recurrent connections. The learning algorithm is developed which uses the same cost function for setting all free parameters, those of the denoising unit and those of the neural network. It is illustrated that the proposed model outmatches the models without denoising unit and/or without recurrent connections in noisy time series prediction.
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
Preview
Unable to display preview. Download preview PDF.
References
Lotrič, U. (2000) Using Wavelet Analysis and Neural Networks for Time Series Prediction, PhD Thesis, University of Ljubljana, Faculty of Computer and Information Science, Ljubljana
Lotrič, U., Dobnikar, A. (2001) Wavelet based smoothing in time series prediction with neural networks. In Kŭrková, V., Steele, N., Nerudá, R., Kárný, M. (eds.) Artificial Neural Nets and Genetic Algorithms: Proceedings of the International Conference in Prague, Springer, Wien, pp. 43–46
Lotrič, U. (2002) Wavelet based denoising integrated into multilayered perceptron. Neurocomputing, submitted for publication, http://laspp.fri.uni-lj.si/uros/publications.htm
Daubechies, I. (1992) Ten lectures on Wavelets, SIAM, Philadelphia
Donoho, D. L., Johnstone, I. M. (1994) Ideal spatial adaptation by wavelet shrinkage. Biometrika 81:425–455
Haykin, S. (1999) Neural Networks: A Comprehensive Foundation, 2nd edition, Prentice-Hall, New Jersey
Williams, R. J., Zipser, D. (1989) A learning algorithm for continually running fully recurrent neural network. Neural Computation 1:270–280
Hagan, M. T., Menhaj,M. B. (1994) Training feedforward networks with the marquardt algorithm. IEEE Transactions on Neural Networks 5(6):989–993
Schuster, H. G. (1984) Deterministic Chaos. An Introduction, Physik, Weinheim
Sunspot index data center, Royal observatory of Belgium (2001) Yearly definitive sunspot number, http://sidc.oma.be.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Wien
About this paper
Cite this paper
Lotrič, U., Dobnikar, A. (2003). Recurrent neural network with integrated wavelet based denoising unit. In: Pearson, D.W., Steele, N.C., Albrecht, R.F. (eds) Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-0646-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-7091-0646-4_8
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-00743-3
Online ISBN: 978-3-7091-0646-4
eBook Packages: Springer Book Archive