Please use this identifier to cite or link to this item:
https://dspace.ncfu.ru/handle/20.500.12258/3188
Title: | An efficient method of error correction in fault-tolerant modular neurocomputers |
Authors: | Chervyakov, N. I. Червяков, Н. И. Lyakhov, P. A. Ляхов, П. А. Babenko, M. G. Бабенко, М. Г. Garyanina, A. I. Гарянина, А. И. Lavrinenko, I. N. Лавриненко, И. Н. Lavrinenko, A. V. Лавриненко, А. В. Deryabin, M. A. Дерябин, М. А. |
Keywords: | Artificial neural network;Chinese remainder theorem (CRT);Fault-tolerance;Mixed radix conversion;Residue number system (RNS);Network architecture |
Issue Date: | 2016 |
Publisher: | Elsevier |
Citation: | Chervyakov, N.I., Lyakhov, P.A., Babenko, M.G., Garyanina, A.I., Lavrinenko, I.N., Lavrinenko, A.V., Deryabin, M.A. An efficient method of error correction in fault-tolerant modular neurocomputers // Neurocomputing. - 2016. - Volume 205. - Pages 32-44 |
Series/Report no.: | Neurocomputing |
Abstract: | In this paper, we propose the architecture of a fault-tolerant unit in a modular neurocomputer that is based on decoding with computation of errors syndromes on redundant moduli and implemented using FPGA and a finite ring neural network. The computational complexity of the proposed architecture is about 80% less in comparison with that of the architecture based on number projections in the mixed radix number system |
URI: | https://www.scopus.com/record/display.uri?eid=2-s2.0-84969931011&origin=resultslist&sort=plf-f&src=s&nlo=&nlr=&nls=&sid=4571c9c342bce71328dbf4646312b3f0&sot=aff&sdt=cl&cluster=scopubyr%2c%222016%22%2ct&sl=174&s=AF-ID%28%22North+Caucasus+Federal+University%22+60070541%29+OR+AF-ID%28%22Stavropol+State+University%22+60070961%29+OR+AF-ID%28%22stavropolskij+Gosudarstvennyj+Tehniceskij+Universitet%22+60026323%29&relpos=27&citeCnt=9&searchTerm= http://hdl.handle.net/20.500.12258/3188 |
Appears in Collections: | Статьи, проиндексированные в SCOPUS, WOS |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
scopusresults 422 .pdf Restricted Access | 62.23 kB | Adobe PDF | View/Open | |
WoS 256 .pdf Restricted Access | 105.69 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.