Abstract
This paper describes the procedure of creating a neural network on the basis of the “etalon” (sample) method. The algorithm for the calculation of the weight table for the neural network connections is adduced and doesn’t need network training. The technology of the optimum creation of the neural network layers is described. The possibility is pointed out to use such an approach for the recognition of curves and symbolic images. An algorithm for the optimal selection of samples from a tested data set is adduced.
Similar content being viewed by others
References
Wasserman F., Neurocomputing. Theory and Practice. (In Russian), Moscow, Mir, 1992.
Golovko V.L., Neural network: training, organization and application / Ed. by A.I. Galushkin. Scient. Ser. “Neurocomputers and their application”, vol. 4 — Moscow, IPRZHR, 2001.
Birger I.A., Technical diagnostics. Moscow, Mashinostroenie, 1978.
Geidarov P.Sh., Increasing identification reliability of hand written characters, based on position-binary recognition technology, Izw. NAN Azerb., Ser. phiz.-math. & techn. Nauk, vol. XXV, no. 2, 2005, pp. 64–69.
Geidarov P.Sh., Algorithm of position-binary recognition of characters. Izw. NAN Azerb., Ser. phiz.-math. & techn. Nauk, vol. XXV, no. 3, 2005, pp. 129–134.
Geidarov P.Sh., Structural indication method for recognition of hand written characters. Izw. NAN Azerb., Ser. phiz.-math. & techn. Nauk, vol. XXV, no. 3, 2005, pp. 65–70.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © P.Sh. Geidarov, 2009, published in Avtomatika i Vychislitel’naya Tekhnika, 2009, No. 4, pp. 48–57.
About this article
Cite this article
Geidarov, P.S. Neural networks on the basis of the sample method. Aut. Conrol Comp. Sci. 43, 203–210 (2009). https://doi.org/10.3103/S0146411609040063
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411609040063