Abstract
Conditions are determined under which, for pattern recognition problems with standard information (Ω-regular problems), a correct algorithm and a six-level spatial neural network reproducing the calculations performed by the correct algorithm can be constructed. The proposed approach to constructing the neural network is not related to the traditional approach based on minimizing a functional.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
S. Haykin, Neural Networks and Learning Machines, 3rd ed. (Prentice Hall, Englewood Cliffs, 2009).
A. Bauer, N. Gornitz, F. Biegler, K.-R. Muller, and M. Kloft, IEEE Trans. 25 (5), 870–881 (2014).
Yu. I. Zhuravlev, Kibernetika, No. 2, 37–45 (1978).
Yu. I. Zhuravlev, Selected Works (Magistr, Moscow, 1998) [in Russian].
A. E. Dyusembaev and D. Kaliazhdarov, Dokl. Math. 91 (2), 236–239 (2015).
A. E. Dyusembaev, USSR Comput. Math. Math. Phys. 22 (6), 217–226 (1982).
A. E. Dyusembaev, USSR Comput. Math. Math. Phys. 23 (6), 126–132 (1983).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © A.E. Dyusembaev, 2017, published in Doklady Akademii Nauk, 2017, Vol. 473, No. 2, pp. 127–130.
Rights and permissions
About this article
Cite this article
Dyusembaev, A.E. An approach to the solution of recognition problems using neural networks. Dokl. Math. 95, 125–128 (2017). https://doi.org/10.1134/S1064562417020053
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064562417020053