Abstract
The paper presents a novel approach to the construction and learning of linear neural networks based on fast orthogonal transforms. The orthogonality of basic operations associated with the algorithm of a given transform is used in order to substantially reduce the number of adapted weights of the network. Two new types of neurons corresponding to orthogonal basic operations are introduced and formulas for architecture-independent error backpropagation and weights adaptation are presented.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Osowski, S.: Neural networks for information processing (in Polish) OWPW, Warsaw (2000)
Rutkowski, L.: Methods and techniques of artificial intelligence (in Polish) Polish Scientific Publishers PWN (2005)
Wang, Z.: Fast algorithms for the discrete W transform and for the discrete Fourier transform. IEEE Trans. on Acoustics, Speech, and Signal Processing 32, 803–816 (1984)
Yatsymirskii, M.N.: Fast algorithms for the discrete cosine transformation. Comput. Maths Math. Phys. 33, 267270 (1993)
Egner, S., Püschel, M.: Automatic generation of fast discrete signal transforms. IEEE Trans. on Signal Processing 49, 1992–2002 (2001)
Jacymirski, M., Szczepaniak, P.S.: Neural realization of fast linear filters. In: Proc. of the 4th EURASIP - IEEE Region 8 International Symposium on Video/Image Processing and Multimedia Communications, pp. 153–157 (2002)
Szczepaniak, P.S.: Intelligent computations, fast transforms and classifiers (in Polish) EXIT Academic Publishing House, Warsaw (2004)
Rabiner, L.R., Gold, B.: Theory and application of digital signal processing. Prentice-Hall, Englewood Cliffs (1975)
Jacymirski, M.: Fast homogeneous algorithms of cosine transforms, type II and III with tangent multipliers, pp. 727–741. AGH University of Science and Technology Press, Cracow (2003)
Yatsymirskyy, M.M.: Shifted in the time and frequency domains cosine and sine transforms fast algorithms with homogeneous structure (in Russian), Kiev. Izvestiya Vysshikh Uchebnykh Zavedenii, Radioelektronika, vol. 43, pp. 66–75 (2000)
Ahmed, N., Rao, K.R.: Orthogonal transforms for digital signal processing. Springer, New York (1975)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stasiak, B., Yatsymirskyy, M. (2006). Fast Orthogonal Neural Networks. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M. (eds) Artificial Intelligence and Soft Computing – ICAISC 2006. ICAISC 2006. Lecture Notes in Computer Science(), vol 4029. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11785231_16
Download citation
DOI: https://doi.org/10.1007/11785231_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-35748-3
Online ISBN: 978-3-540-35750-6
eBook Packages: Computer ScienceComputer Science (R0)