Please use this identifier to cite or link to this item: https://er.nau.edu.ua/handle/NAU/18513
Title: NEURAL NETWORK TECHNOLOGIES FOR RECOGNITION CHARACTERS
Authors: Kucherov, D.P.
Ohirko, I.V.
Ohirko, O.I.
Golenkovskaya, T.I.
Keywords: Neural networks; learning; gradient; Levenberg–Marquardt method; synthetic image
Issue Date: Dec-2015
Publisher: National aviation university
Abstract: The process of neural networks modeling for pattern recognized problem of printed characters consid-ered in this paper. Learning for pattern recognition preparing for a limited set of synthetic characters. It assumes the two-layer neural network training. The convergence of three learning algorithms is stud-ied. They are packet-based adjustment of weights and biases, the gradient, the algorithm based on the computation of the Jacobian function weights. The article provides recommendations for the installa-tion of the initial parameters for a set of tools Neural Networks Toolbox software Matlab. Experimental results for different settings customer networks given that confirms these propositions.
Description: This paper devoted the character recognition.
URI: http://er.nau.edu.ua/handle/NAU/18513
ISSN: 1990-5548
Appears in Collections:Наукові статті кафедри комп’ютеризованих систем управління

Files in This Item:
File Description SizeFormat 
Razdel_3-2_Kucherov_new.docxОсновная статья127.04 kBMicrosoft Word XMLView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.