Abstract
This article is dedicated to description of clearly defined neural networks on the basis of metric methods of recognition in which realization quantity of layers, neurons and connections are strictly determined according to the task initial conditions: quantity of images, samples and features. Also it describes the algorithm of training sample selection, as well problems related to opportunities of neural network architecture multitask application and opportunities of neural networks configuration optimization with usage of the clusterization algorithm applying to tasks of recognition and usage of network sequential recognition algorithm.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Geidarov, P.Sh., Neural networks on the basis of the sample method, Aut. Control Comput. Sci., 2009, vol 43, no. 4, pp. 203–210.
Birger, I.A., Technical Diagnostics, M.: Machine Building, 1978.
Wasserman, F., Neurocomputing, Theory and Practice, M.: Mir, 1992.
Mirkes, E.M., Neurocomputer, Project of Standard, Novosibirsk: Nauka, 1998.
Golovko, V.L., Neural Network: Training, Organization and Application, Moscow: IPRZHR, 2001, vol. 4.
Barskiy, A.B., Neural Networks: Recognition, Management, Decision-Making, Moscow: Finance and Statistics, 2004.
Geidarov, P.S., Increasing identication reliability of hand printed characters, Trans. NAS Azerbaijan, Baku, 2005, vol. XXV, no. 2, pp. 64–69.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Geidarov, P.S. Clearly defined neural network architecture. Opt. Mem. Neural Networks 24, 209–219 (2015). https://doi.org/10.3103/S1060992X15030054
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X15030054