Abstract
Wavelet transformation is a powerful method of signal processing which uses decomposition of the studied signal over a special basis with unique properties, the most important of which are its compactness and multiresolution: wavelet functions are produced from the mother wavelet by transition and dilation. Wavelet neural networks (WNN) are a family of approximation algorithms that use wavelet functions to decompose the approximated function. If only approximation and no inverse transformation is needed, the values of transition and dilation coefficients may be determined during network training, and the windows corresponding to various wavelet functions may overlap, making the whole system much more efficient. Here we present a new type of a WNN – Adaptive Window WNN (AWWNN), in which window positions and wavelet levels are determined with a special iterative procedure. Two modifications of AWWNN are tested against linear model and multi-layer perceptron on Mackey-Glass benchmark prediction problem.
This study has been performed with financial support from the Ministry of Education and Science of Russia, agreement no.14.604.21.0163, project ID RFMEFI60417X0163.
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
Efitorov, A., Dolenko, T., Burikov, S., Laptinskiy, K., Dolenko, S.: Solution of an inverse problem in raman spectroscopy of multi-component solutions of inorganic salts by artificial neural networks. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9887, pp. 355–362. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-44781-0_42
Gorbachenko, V.I., Lazovskaya, T.V., Tarkhov, D.A., Vasilyev, A.N., Zhukov, M.V.: Neural network technique in some inverse problems of mathematical physics. In: Cheng, L., Liu, Q., Ronzhin, A. (eds.) ISNN 2016. LNCS, vol. 9719, pp. 310–316. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-40663-3_36
Wehrens, R.: Chemometrics with R: Multivariate Data Analysis in the Natural Sciences and Life Sciences. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-17841-2. p. 288, ISBN: 3642178405
Efitorov, A., Burikov, S., Dolenko, T., Laptinskiy, K., Dolenko, S.: Significant feature selection in neural network solution of an inverse problem in spectroscopy. Procedia Comput. Sci. 66, 93–102 (2015)
Strang, G., Nguyen, T.: Wavelets and Filter Banks, 2nd edn. Wellesley-Cambridge Press, Wellesley (1996). 520 pp
Mallat, S.G.: A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans. Patt. Recogn. Mach. Intell. 11(7), 674–693 (1989)
Zhang, Q., Benveniste, A.: Wavelet networks. IEEE Trans. Neural Netw. 6, 889–898 (1992). https://doi.org/10.1109/72.16559
Malada, H.R., Ivakhnenko, A.G.: Inductive Learning Algorithms for Complex Systems Modeling. CRC Press (1994)
Efitorov, A., Dolenko, S.: A new type of a wavelet neural network. Opt. Mem. Neural Netw. (Information Optics) 27(3), 152–160 (2018). http://doi.org/10.3103/S1060992X18030050
Ouahabi, A. (Ed.): Signal and Image Multiresolution Analysis. Wiley (2012). 301 pp
Mallat, S.: A Wavelet Tour of Signal Processing. Academic Press, San Diego (2008). 832 pp
Kingma, D.P., Ba, J.L.: Adam: a Method for Stochastic Optimization. Conference paper ICLR 2015 (2015). arXiv:1412.6980
Hramov, A.E., Koronovskii, A.A., Makarov, V.A., Pavlov, A.N., Sitnikova, E.: Wavelets in Neuroscience. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-43850-3. 318 pp
Mackey, M., Glass, L.: Oscillation and chaos in physiological control systems. Science 197(4300), 287–289 (1977). https://doi.org/10.1126/science.267326
Keras: The Python Deep Learning Library. https://keras.io/
TensorFlowTM: An open source machine learning framework for everyone. https://www.tensorflow.org/
Tange, O.: GNU Parallel 2018, March 2018. ISBN 9781387509881. https://doi.org/10.5281/zenodo.1146014
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014). http://jmlr.org/papers/v15/srivastava14a.html
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Efitorov, A., Shiroky, V., Dolenko, S. (2018). A Neural Network of Multiresolution Wavelet Analysis. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11140. Springer, Cham. https://doi.org/10.1007/978-3-030-01421-6_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-01421-6_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01420-9
Online ISBN: 978-3-030-01421-6
eBook Packages: Computer ScienceComputer Science (R0)