Abstract
The Kolmogorov theorem gives that the representation of continuous and bounded real-valued functions of n variables by the superposition of functions of one variable and addition is always possible. Based on the fact that each proof of the Kolmogorov theorem or its variants was a constructive one so far, there is the principal possibility to attain such a representation. This paper reviews a procedure for obtaining the Kolmogorov representation of a function, based on an approach given by David Sprecher. The construction is considered in more detail for an image function.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Kolmogorov, A.N.: On the representation of continuous functions of several variables by superpositions of continuous functions of one variable and addition. Doklady Akademii Nauk SSSR 114 (1957) 679–681 (in Russian).
Hecht-Nielsen, R.: Kolmogorov’s mapping neural network existence theorem. In: Proceedings of the First International Conference on Neural Networks. Volume III., IEEE Press, New York (1987)11–13
Kreinovich, V., Nguyen, H., Sprecher, D.: Normal forms for fuzzy logic — an application of kolmogorov’s theorem. Technical Report UTEP-CS-96-8, University of Texas at El Paso (1996)
Nguyen, H., Kreinovich, V.: Kolmogorov’s theorem and its impact on soft computing. In Yager, R.R., Kacprzyk, J., eds.: The Ordered Weighted Averaging operators. Theory and Applications. Kluwer Academic Publishers (1997) 3–17
Sprecher, D.: On the structure of continuous functions of several variables. Transcations of the American Mathematical Society 115 (1965) 340–355
Cotter, N.E., Guillerm, T.J.: The CMAC and a theorem of Kolmogorov. Neural Networks 5 (1992) 221–228
Sprecher, D.: A numerical implementation of Kolmogorov’s superpositions I. Neural Networks 9 (1996) 765–772
Sprecher, D.: A numerical implementation of Kolmogorov’s superpositions II. Neural Networks 10 (1997) 447–457
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
Köppen, M. (2002). On the Training of a Kolmogorov Network. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5_77
Download citation
DOI: https://doi.org/10.1007/3-540-46084-5_77
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44074-1
Online ISBN: 978-3-540-46084-8
eBook Packages: Springer Book Archive