Abstract
The feasibility of function of errors with fractional exponent for solving of a problem of optimization and tutoring of neural networks was theoretically explored. The analytical expressions for estimation of parameters of the models or weight factors were obtained. The algorithms were designed and the numerical experiment on actual economic datas was held, where the efficiency of an offered procedure is shown.
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
Widrow B., Hoff M. Adaptive switching circuits // In 1960 IRE WESCON Convention Record. DUNNO. 1960. P. 96–104.
Rutkowska D., Pilicki M., Rutkowski L. (Sieci neuronowe, algorytmy genetyczne i systemy rozmyte. Warszawa. PWN. 1997. 410 S.)
Kolmogorov A.N., Fomin S.V. Elements of theory of functions and analyze of functions. Moskow: Nauka. 1968. 496 C.
Samko S. G., Kilbas A. A. and Marichev O. I. Fractional integrals and derivatives. Theory and applications. 1993. Gordon and Breach, New York, etc.
Erdelyi A., Magnus W., Oberhettinger F. and Tricorni F.G. Higher transcendental functions. Vol. 1. 1953. McGraw-Hill, New York, etc.
T. Masters. Practical neural network recipies in C ++. (Academic Press, Inc., 1993 ).
Osowski S. Sieci neuronowe w ujeciu algorytmicznym. Wydanie drugie. (Warszawa. WNT. 1996. 346 S.).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Grinko, A.P., Karpuk, M.M. (2002). Modification of Method of Least Squares for Tutoring a Neural Networks. In: Kłopotek, M.A., Wierzchoń, S.T., Michalewicz, M. (eds) Intelligent Information Systems 2002. Advances in Soft Computing, vol 17. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1777-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1777-5_16
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-1509-2
Online ISBN: 978-3-7908-1777-5
eBook Packages: Springer Book Archive