Geodesic
Teaching big hybrid neural networks for time series prediction
Informacionnye tehnologii i vyčislitelnye sistemy, no. 2 (2017), pp. 54-61

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

The article describes hybrid approach in neural networks, used in prediction of time series, as well as the specific aspects of teaching hybrid neural networks consisting of Self-Organizing Maps (SOM) and Multilayer Perсeptron (MLP). Also, paper contains the results, gained during the process of building and teaching the large hybrid neural network and the new algorithm of equitable teaching for self-organizing layer.
Keywords: neural nets, hybrid neural nets, self-organizing maps, time series prediction, function approximation. 
@article{ITVS_2017_2_a4,
     author = {D. Y. Nagornykh},
     title = {Teaching big hybrid neural networks for time series prediction},
     journal = {Informacionnye tehnologii i vy\v{c}islitelnye sistemy},
     pages = {54--61},
     publisher = {mathdoc},
     number = {2},
     year = {2017},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ITVS_2017_2_a4/}
}
TY  - JOUR
AU  - D. Y. Nagornykh
TI  - Teaching big hybrid neural networks for time series prediction
JO  - Informacionnye tehnologii i vyčislitelnye sistemy
PY  - 2017
SP  - 54
EP  - 61
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ITVS_2017_2_a4/
LA  - ru
ID  - ITVS_2017_2_a4
ER  - 
%0 Journal Article
%A D. Y. Nagornykh
%T Teaching big hybrid neural networks for time series prediction
%J Informacionnye tehnologii i vyčislitelnye sistemy
%D 2017
%P 54-61
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ITVS_2017_2_a4/
%G ru
%F ITVS_2017_2_a4
D. Y. Nagornykh. Teaching big hybrid neural networks for time series prediction. Informacionnye tehnologii i vyčislitelnye sistemy, no. 2 (2017), pp. 54-61. http://geodesic.mathdoc.fr/item/ITVS_2017_2_a4/