Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.12258/528
Title: Increasing of convolutional neural network performance using residue number system
Authors: Chervyakov, N. I.
Червяков, Н. И.
Lyakhov, P. A.
Ляхов, П. А.
Valueva, M. V.
Валуева, М. В.
Keywords: Convolutional Neural Network (CNN);Image processing;Pattern recognition;Residue number system (RNS)
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Chervyakov, N.I., Lyakhov, P.A., Valueva, M.V. Increasing of convolutional neural network performance using residue number system // Proceedings - 2017 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2017. - 2017. - статья № 8109855. - pp. 135-140.
Series/Report no.: Proceedings - 2017 International Multi-Conference on Engineering, Computer and Information Sciences, SIBIRCON 2017
Abstract: This paper considers the method of pattern recognition based on a convolutional neural network using Sobel filters. Parameters of the convolutional neural network blocks were chosen experimentally by software modeling in MATLAB. We presents the architecture of the convolutional neural network constructed with residue number system for delay minimization. Using of special type of modules allows to accelerate the work of the device by 37,4% as compared to using a binary number system and by 18,5% as compared to using a known residue number system realization
URI: https://www.scopus.com/record/display.uri?eid=2-s2.0-85040520452&origin=resultslist&sort=plf-f&src=s&nlo=1&nlr=20&nls=afprfnm-t&affilName=nort*+caucas*+fed*+univ*&sid=6e44c4739f67eaef119fa92298a82e4b&sot=afnl&sdt=sisr&sl=53&s=%28AF-ID%28%22North+Caucasus+Federal+University%22+60070541%29%29&ref=%28Increasing+of+convolutional+neural+network+performance+using+residue+number%29&relpos=0&citeCnt=0&searchTerm=
https://dspace.ncfu.ru:443/handle/20.500.12258/528
Appears in Collections:Статьи, проиндексированные в SCOPUS, WOS

Files in This Item:
File Description SizeFormat 
scopusresults (75).pdf62.44 kBAdobe PDFThumbnail
View/Open
WoS 43 .pdf80.58 kBAdobe PDFThumbnail
View/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.