Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.12258/12120
Title: Application of the residue number system to reduce hardware costs of the convolutional neural network implementation
Authors: Valueva, M. V.
Валуева, М. В.
Nagornov, N. N.
Нагорнов, Н. Н.
Lyakhov, P. A.
Ляхов, П. А.
Valuev, G. V.
Валуев, Г. В.
Chervyakov, N. I.
Червяков, Н. И.
Keywords: Convolutional neural networks;Field-programmable gate array (FPGA);Image processing;Quantization noise;Residue number system (RNS);Convolutional neural networks
Issue Date: 2020
Publisher: Elsevier B.V.
Citation: Valueva, M.V., Nagornov, N.N., Lyakhov, P.A., Valuev, G.V., Chervyakov, N.I. Application of the residue number system to reduce hardware costs of the convolutional neural network implementation // Mathematics and Computers in Simulation. - 2020. - Volume 177. - Pages 232-243
Series/Report no.: Mathematics and Computers in Simulation
Abstract: Convolutional neural networks are a promising tool for solving the problem of pattern recognition. Most well-known convolutional neural networks implementations require a significant amount of memory to store weights in the process of learning and working. We propose a convolutional neural network architecture in which the neural network is divided into hardware and software parts to increase performance and reduce the cost of implementation resources. We also propose to use the residue number system (RNS) in the hardware part to implement the convolutional layer of the neural network. Software simulations using Matlab 2018b showed that convolutional neural network with a minimum number of layers can be quickly and successfully trained. The hardware implementation of the convolution layer shows that the use of RNS allows to reduce the hardware costs on 7.86%–37.78% compared to the two's complement implementation. The use of the proposed heterogeneous implementation reduces the average time of image recognition by 41.17%
URI: http://hdl.handle.net/20.500.12258/12120
Appears in Collections:Статьи, проиндексированные в SCOPUS, WOS

Files in This Item:
File Description SizeFormat 
scopusresults 1286 .pdf904.7 kBAdobe PDFView/Open
WoS 848 .pdf174.67 kBAdobe PDFView/Open


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