Abstract
In the paper, the use of neural networks for the implementation of fast algorithms of spectral transformations is discussed. It is shown that the fast algorithms are particular cases of fast neural networks (FNNs). Methods for parametric tuning FNNs to a given system of basis functions are suggested. Neural network implementations of the fast Walsh and wavelet transformations and the fast Fourier, Vilenkin–Christiansen, and Haar transforms are constructed. The discussions are illustrated by examples.
Similar content being viewed by others
REFERENCES
Galushkin, A.I., Modern Trends of the Development of the Neural Computer Technology in Russia, Otkrytye sistemy, 1997, no. 4, pp. 25-28.
Heiht-Nilsen, R., Neurocomputing: History, State of the Art, Prospects, Otkrytye sistemy, 1998, nos. 4-5 (30-31), pp. 23-28.
Neirokomp'yutery (Neurocomputers), University Handbook, Galushkin, A.I., Ed., Moscow: IPRZhR, 2000, vol.3.
Dorogov, A.Yu., Structural Synthesis of Fast Neural Networks, Neirokomp'yuter, 1999, no. 1, pp. 11-24.
Dorogov, A.Yu., Structure Synthesis of Fast Neural Networks, in Neurocomputers Design and Application, New York, 2000, vol. 1, no. 1, pp. 1-18.
Good, I.J., The Interaction Algorithm and Practical Fourier Analysis, J. Royal Statistical Soc., 1958, Ser. B, vol. 20, no. 2, pp. 361-372.
Andrews, H.C. and Caspari, K.L., A General Technique for Spectral Analyis, IEEE Trans. Comput., 1970, vol. C-19, no. 1, pp. 16-25.
Andrews, H.C., Primenenie vychislitel'nykh mashin dlya obrabotki izobrazhenii (Application of Computers to Image Processing), Moscow, 1977.
Solodovnikov, A.I., Kanatov, I.I., and Spivakovskii, A.M., Orthogonal Bases Synthesis Based on the Generalized Spectral Kernel, in Voprosy teorii sistem avtomaticheskogo upravleniya (Theoretical Issues of Automatic Control Systems), Leningrad: LGU, 1976, vol. 2, pp. 99-112.
Labunets, V.G., A Unified Approach to Fast Transformation Algorithms, in Primenenie ortogonal'nykh metodov pri obrabotke signalov i analize sistem (Application of Orthogonal Methods to Signal Processing and Systems Analysis), Sverdlovsk: UPI, 1980, pp. 4-14.
Dorogov, A.Yu. and Solodovnikov, A.I., Reconstructable Orthogonal Bases for Adaptive Spectral Transformations, in Metody i sredstva obrabotki prostranstvennovremennykh signalov (Methods and Tools for Processing Space-Time Signals), Sverdlovsk: UPI, 1988, pp. 18-26.
Dorogov, A.Yu., Structural Synthesis of Modular Weakly Connected Neural Networks. I. Methodology of Structural Synthesis of Modular Neural Networks, Kibern. Sistemnyi Analiz, 2001, no. 2, pp. 34-42.
Dorogov, A.Yu., Structural Synthesis of Modular Weakly Connected Neural Networks. I. Methodology of Structural Synthesis of Modular Neural Networks, Cybernetics System Analysis, 2001, vol. 37, no. 2, pp. 175-181.
Rabiner, L. and Gold, B., Theory and Application of Digital Signal Processing, Englewood Cliffs: Prentice-Hall, 1975. Translated under the title Teoriya i primenenie tsifrovoi obrabotki signalov, Moscow: Mir, 1978.
Good, I.J., Relationship between Two Fast Fourier Transforms, Application of Number Theory to Signal Processing, McCellan, J.H. and Reder, C.M., Eds. Translated under the title Primenenie teorii chisel v tsifrovoi obrabotke signalov, Moscow: Radio i Svyaz', 1983.
Trakhtman, A.M. and Trakhtman, V.A., Osnovy teorii diskretnykh signalov na konechnykh intervalakh (Theory of Discrete Signals on Finite Intervals), Moscow: Sovetskoe Radio, 1975.
Yaroslavskii, L.P., Vvedenie v tsifrovuyu obrabotku izobrazhenii (Introduction to Image Processing), Moscow: Sovetskoe Radio, 1979.
Dorogov, A.Yu., Bystrye neironnye seti (Fast Neural Networks), St. Petersburg: Izd. Sankt-Peterburgskogo Univ., 2002.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Dorogov, A.Y. Implementation of Spectral Transformations in the Class of Fast Neural Networks. Programming and Computer Software 29, 187–198 (2003). https://doi.org/10.1023/A:1024966508452
Issue Date:
DOI: https://doi.org/10.1023/A:1024966508452