ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION

The paper deals with the application of CUDA-technology on software implementation of direct and reverse passes of artificial neural network (ANN) based on back-propagation algorithm. It is shown that introduction of «imaginary» neurons helps to adapt the topology of the neural network to be trained...

Full description

Saved in:
Bibliographic Details
Main Authors: O. S. Hilko, S. P. Kundas, V. I. Kovalenko
Format: Article
Language:Russian
Published: Educational institution «Belarusian State University of Informatics and Radioelectronics» 2019-06-01
Series:Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki
Subjects:
Online Access:https://doklady.bsuir.by/jour/article/view/94
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849772727558209536
author O. S. Hilko
S. P. Kundas
V. I. Kovalenko
author_facet O. S. Hilko
S. P. Kundas
V. I. Kovalenko
author_sort O. S. Hilko
collection DOAJ
description The paper deals with the application of CUDA-technology on software implementation of direct and reverse passes of artificial neural network (ANN) based on back-propagation algorithm. It is shown that introduction of «imaginary» neurons helps to adapt the topology of the neural network to be trained and calculated with CUDA-technology. It is proved that «imaginary» neurons do not affect on the calculations in the back propagation algorithm.
format Article
id doaj-art-1ff96a2da7d34bdd9045d77754951a49
institution DOAJ
issn 1729-7648
language Russian
publishDate 2019-06-01
publisher Educational institution «Belarusian State University of Informatics and Radioelectronics»
record_format Article
series Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki
spelling doaj-art-1ff96a2da7d34bdd9045d77754951a492025-08-20T03:02:15ZrusEducational institution «Belarusian State University of Informatics and Radioelectronics»Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki1729-76482019-06-010610711393ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATIONO. S. Hilko0S. P. Kundas1V. I. Kovalenko2Международный государственный экологический университет им. А.Д. СахароваМеждународный государственный экологический университет им. А.Д. СахароваМеждународный государственный экологический университет им. А.Д. СахароваThe paper deals with the application of CUDA-technology on software implementation of direct and reverse passes of artificial neural network (ANN) based on back-propagation algorithm. It is shown that introduction of «imaginary» neurons helps to adapt the topology of the neural network to be trained and calculated with CUDA-technology. It is proved that «imaginary» neurons do not affect on the calculations in the back propagation algorithm.https://doklady.bsuir.by/jour/article/view/94cuda-технология«мнимый» нейрон
spellingShingle O. S. Hilko
S. P. Kundas
V. I. Kovalenko
ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki
cuda-технология
«мнимый» нейрон
title ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION
title_full ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION
title_fullStr ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION
title_full_unstemmed ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION
title_short ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION
title_sort adaptation of artificial neural networks for cuda technology application
topic cuda-технология
«мнимый» нейрон
url https://doklady.bsuir.by/jour/article/view/94
work_keys_str_mv AT oshilko adaptationofartificialneuralnetworksforcudatechnologyapplication
AT spkundas adaptationofartificialneuralnetworksforcudatechnologyapplication
AT vikovalenko adaptationofartificialneuralnetworksforcudatechnologyapplication