CFP last date
20 January 2025
Call for Paper
February Edition
IJCA solicits high quality original research papers for the upcoming February edition of the journal. The last date of research paper submission is 20 January 2025

Submit your paper
Know more
The week's pick
Responsive image
SFLA-Based Line Balancing and Task Optimization in Master-Slave Controlled Hanger Transportation Systems for Garment Production

Duc Hoang Nguyen
Random Articles
Reseach Article

Parallel Implementation of a Neural Network Learning Algorithm

by S. Volokitin
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 85 - Number 3
Year of Publication: 2014
Authors: S. Volokitin
10.5120/14819-3049

S. Volokitin . Parallel Implementation of a Neural Network Learning Algorithm. International Journal of Computer Applications. 85, 3 ( January 2014), 8-11. DOI=10.5120/14819-3049

@article{ 10.5120/14819-3049,
author = { S. Volokitin },
title = { Parallel Implementation of a Neural Network Learning Algorithm },
journal = { International Journal of Computer Applications },
issue_date = { January 2014 },
volume = { 85 },
number = { 3 },
month = { January },
year = { 2014 },
issn = { 0975-8887 },
pages = { 8-11 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume85/number3/14819-3049/ },
doi = { 10.5120/14819-3049 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:01:30.693064+05:30
%A S. Volokitin
%T Parallel Implementation of a Neural Network Learning Algorithm
%J International Journal of Computer Applications
%@ 0975-8887
%V 85
%N 3
%P 8-11
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

This paper describes parallel implementation of an artificial neural network training algorithm and its effectiveness when applied to performing cryptographic functions. As a cryptographic function a permutations have been used because of its prevalence in complex cryptographic functions such as block ciphers. In order to enhance performance of artificial neural network training algorithm a method of backward propagation of errors has been parallelized.

References
  1. Kotlars P. , Kotulski Z. On application of neural networks for S-box design, in: P. S. Szczepaniak, J. Kacprzyk, A. Niewiadomski, ed. Advances in Web Intelligence, AWIC 2005, LNCS 3528. ?. 243-248. Berlin 2005.
  2. John Viega Network Security with OpenSSL. — 1-st. — O'Reilly Media, USA, June 15, 2002.
  3. L. Bossuet, G. Gogniat, and W. Burleson. Dynamically con?gurable Security for SRAM FPGA Bitstreams. International Journal of Embedded Systems, 2(1-2):73–85, 2006.
  4. T. Blum and C. Paar. High Radix Montgomery Modular Exponentiation on Reconfigurable Hardware. IEEE Transactions on Computers, 50(7):759–764, 2001.
  5. P. Bulens, F. X. Standaert, J. -J. Quisquater, P. Pellegrin, and G. Rouvroy. Implementation of the AES-128 on Virtex-5 FPGAs. In S. Vaudenay, editor, Proceedings of First International Conference on Cryptology in Africa –AFRICACRYPT 2008, volume 5023 of LNCS Series, pages 16–26. Springer-Verlag, 2008.
  6. Rumelhart D. E. , Hinton G. E. , Williams R. J. , Learning Internal Representations by Error Propagation. In: Parallel Distributed Processing, vol. 1, pp. 318—362. Cambridge, MA, MIT Press. 1986.
  7. Veselý, Karel, Burget, Lukas and Grézl, Frantisek. Parallel training of neural networks for speech recognition. ISCA, page 2934-2937, 2010.
  8. Jang, H. , Park, A. & Jung, K. . Neural Network Implementation Using CUDA and OpenMP. DICTA, page 155-161. IEEE Computer Society, 2008.
  9. X. Sierra-Canto, F. Madera-Ramirez, V. Uc-Cetina. Parallel Training of a Back-Propagation Neural Network Using CUDA. ICMLA, page 307-312. IEEE Computer Society, 2010.
  10. S. T. Brassai, L. Bako, G. Pana, S. Dan. Neural control based on RBF network implemented on FPGA. OPTIM 2008, page 41-46, 2008.
Index Terms

Computer Science
Information Sciences

Keywords

Neural network training algorithm parallelism cryptography

Powered by PhDFocusTM