Determining the Weights of A Fourier Series Neural Network on the Basis of the Multidimensional Discrete Fourier Transform

Halawa, Krzysztof

doi:10.2478/v10006-008-0033-8

Abstract

This paper presents a method for training a Fourier series neural network on the basis of the multidimensional discrete Fourier transform. The proposed method is characterized by low computational complexity. The article shows how the method can be used for modelling dynamic systems.

References

Bracewell R. (1999). The Fourier Transform and Its Applications, 3rd Edn., McGraw-Hill, New York, NY.
Search in Google Scholar
Chu E. and George A. (2000). Inside the FFT Black Box: Serial and Parallel Fast Fourier Transform Algorithms, CRC Press, Boca Raton, FL.10.1201/9781420049961
Search in Google Scholar
Dutt A. and Rokhlin V. (1993). Fast Fourier transforms for nonequispaced data, Journal of Scientific Computing14(6): 1368-1393.10.1137/0914081
Search in Google Scholar
Gonzalez R. C. and Woods R. E. (1999). Digital Image Processing, 2nd Edn., Prentice-Hall, Inc., Boston, MA.
Search in Google Scholar
Halawa K. (2008). Fast method for computing outputs of Fourier neutral networks, in: K. Malinowski and L. Rutkowski, Eds., Control and Automation: Current Problems and Their Solutions, EXIT, Warsaw, pp. 652-659, (in Polish).
Search in Google Scholar
Hyvarinen A. and Oja E. (2000). Independent component analysis: Algorithms and applications, Neural Networks13(4): 411-430.10.1016/S0893-6080(00)00026-5
Search in Google Scholar
Joliffe I. T. (1986). Principal Component Analysis, Springer-Verlag, New York, NY.10.1007/978-1-4757-1904-8
Search in Google Scholar
Kegl B., Krzyżak A., Linder T. and Zeger K. (2000). Learning and design of principal curves, IEEE Transactions on Pattern Analysis and Machine Intelligence22(13): 281-297.10.1109/34.841759
Search in Google Scholar
Li H. and Sun Y. (2005). The study and test of ICA algorithms, Proceedings of the International Conference on Wireless Communications, Networking and Mobile Computing, Wuhan, China, pp. 602-605.
Search in Google Scholar
Liu Q. H. and Nyguen N. (1998). An accurate algorithm for nonuniform fast Fourier transforms, Microwave and Guided Wave Letters8(1): 18-20.10.1109/75.650975
Search in Google Scholar
Nelles O. (2001). Nonlinear System Identification: From Classical Approaches to Neural Network and Fuzzy Models, Springer-Verlag, Berlin.
Search in Google Scholar
Rafajłowicz E. and Pawlak M. (1997). On function recovery by neural networks based on orthogonal expansions, Nonlinear Analysis, Theory and Applications30(3): 1343-1354.10.1016/S0362-546X(97)00223-X
Search in Google Scholar
Rafajłowicz E. and Skubalska-Rafajłowicz E. (1993). FFT in calculating nonparametric regression estimate based on trigonometric series, International Journal of Applied Mathematics and Computer Science3(4): 713-720.
Search in Google Scholar
Sher C. F., Tseng C. S. and Chen C. (2001). Properties and performance of orthogonal neural network in function approximation, International Journal of Intelligent Systems16(12): 1377-1392.10.1002/int.1065
Search in Google Scholar
Tseng C. S. and Chen C. S. (2004). Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation, International Journal of Intelligent Systems19(12): 1257-1275.10.1002/int.20047
Search in Google Scholar
Van Loan C. (1992). Computational Frameworks for the Fast Fourier Transform, SIAM, Philadelphia, PA.10.1137/1.9781611970999
Search in Google Scholar
Walker J. (1996). Fast Fourier Transforms, CRC Press, Boca Raton, FL.
Search in Google Scholar
Zhu C., Shukla D. and Paul F. (2002). Orthogonal functions for system identification and control, in: C. T. Leondes (Ed.), Neural Networks Systems, Techniques and Apllications: Control and Dynamic Systems, Academic Press, San Diego, CA, pp. 1-73.
Search in Google Scholar

Determining the Weights of A Fourier Series Neural Network on the Basis of the Multidimensional Discrete Fourier Transform

Abstract

Paradigm

My account