Geodesic
Study of multilayer perceptron accuracy improvement under fixed number of neuron
Informacionnye tehnologii i vyčislitelnye sistemy, no. 1 (2016), pp. 96-105

Voir la notice de l'article provenant de la source Math-Net.Ru

In this article multilayer perceptron accuracy improvement of real time recognition system under time limitations was explored. To solve this task two level tree of classifiers was used. The top level of the tree is a fast selector gotten without supervised training, and the bottom level is a set of neural net classifiers trained on the corresponding training sets. These scheme allows to increase the number of neurons used in recognition under the same processing time, that helps to increase generalisation power of the classifier. Recognition of embossed symbols on plastic cards was used as model task.
Keywords: machine learning, feature spaces, real time recognition systems.
Mots-clés : OCR, multilayer perceptron 
@article{ITVS_2016_1_a8,
     author = {S. A. Gladilin and D. P. Nikolaev and D. V. Polevoi and N. A. Sokolova},
     title = {Study of multilayer perceptron accuracy improvement under fixed number of neuron},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {96--105},
     publisher = {mathdoc},
     number = {1},
     year = {2016},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2016_1_a8/}
}
TY  - JOUR
AU  - S. A. Gladilin
AU  - D. P. Nikolaev
AU  - D. V. Polevoi
AU  - N. A. Sokolova
TI  - Study of multilayer perceptron accuracy improvement under fixed number of neuron
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2016
SP  - 96
EP  - 105
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2016_1_a8/
LA  - ru
ID  - ITVS_2016_1_a8
ER  - 
%0 Journal Article
%A S. A. Gladilin
%A D. P. Nikolaev
%A D. V. Polevoi
%A N. A. Sokolova
%T Study of multilayer perceptron accuracy improvement under fixed number of neuron
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2016
%P 96-105
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2016_1_a8/
%G ru
%F ITVS_2016_1_a8
S. A. Gladilin; D. P. Nikolaev; D. V. Polevoi; N. A. Sokolova. Study of multilayer perceptron accuracy improvement under fixed number of neuron. Informacionnye tehnologii i vyčislitelnye sistemy, no. 1 (2016), pp. 96-105. http://geodesic.mathdoc.fr/item/ITVS_2016_1_a8/