ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION
- Р Р‡.МессенРТвЂВВВВВВВВжер
- РћРТвЂВВВВВВВВнокласснРСвЂВВВВВВВВРєРСвЂВВВВВВВВ
- LiveJournal
- Telegram
- ВКонтакте
- РЎРєРѕРїРСвЂВВВВВВВВровать ссылку
Full Text:
Abstract
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.
About the Authors
O. S. Hilko
Международный государственный экологический университет им. А.Д. Сахарова
Belarus
Belarus
S. P. Kundas
Международный государственный экологический университет им. А.Д. Сахарова
Belarus
Belarus
V. I. Kovalenko
Международный государственный экологический университет им. А.Д. Сахарова
Belarus
Belarus
References
1. Khil'ko O.S., Kovalenko V.I., Kundas S.P. // Dokl. BGUIR. 2010, № 7 (53). C. 83-88.
2. Kundas S.P., Gishkelyuk I.A., Kovalenko V.I. i dr. Komp'yuternoe modelirovanie migratsii zagryaznyayushchikh veshchestv v prirodnykh dispersnykh sredakh. Mn.: MGEU im. A.D. Sakharova, 2011.
3. Antonov I. // Khaker. 2009, № 127. C. 28-31.
4. Khil'ko O.S. // Doklady BGUIR. 2011, № 4 (58). C. 55-62.
5. Khaikin S. Neironnye seti. Polnyi kurs. SPb : Vil'yams, 2006.
6. Golovko V.A. Neironnye seti: obuchenie, organizatsiya i primenenie. M., 2001.
7. Kundas S.P., Kovalenko V.I., Khil'ko O.S. // Vestnik PGU. 2009. № 9. C. 32-38.
Review
For citations:
Hilko O.S., Kundas S.P., Kovalenko V.I. ADAPTATION OF ARTIFICIAL NEURAL NETWORKS FOR CUDA-TECHNOLOGY APPLICATION. Doklady BGUIR. 2012;(6):107-113. (In Russ.)
Views:
431
ISSN 1729-7648 (Print)
ISSN 2708-0382 (Online)
ISSN 2708-0382 (Online)
Email this article 