Application of the residue number system to reduce hardware costs of the convolutional neural network implementation

DOI10.1016/J.MATCOM.2020.04.031MaRDI QIDQ1998097OpenAlexFDO

Authors M. V. Valueva, N. N. Nagornov, P. A. Lyakhov, G. V. Valuev, N. I. Chervyakov

Publication date 6 March 2021

Published in Mathematics and Computers in Simulation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.matcom.2020.04.031

zbMATH Keywords

image processingresidue number systemconvolutional neural networksfield-programmable gate array (FPGA)quantization noise

Mathematics Subject Classification ID

Algorithms in computer science (68Wxx) Theory of computing (68Qxx) Computational number theory (11Yxx) Elementary number theory (11Axx)

Recommendations

• Method for Convolutional Neural Network Hardware Implementation Based on a Residue Number System
• scientific article; zbMATH DE number 1210941
• A faster algorithm for reducing the computational complexity of convolutional neural networks
• Layer-Parallel Training of Deep Residual Neural Networks

Cites work

• scientific article; zbMATH DE number 2221547 (Why is no real title available?)
• An approximate sign detection method for residue numbers and its application to RNS division
• On Modulo 2^n+1 Adder Design
• Residue number systems. Theory and implementation.
• Residue-to-binary conversion for general moduli sets based on approximate Chinese remainder theorem

Cited in

(5)

• A Study on Affine Transformations and a Novel Universal Prediction Theory
• Multi-input bio-inspired weights and structure determination neuronet with applications in European central bank publications
• Tool path optimization of selective laser sintering processes using deep learning
• CRTf-Based Reverse Converter for RNS with Low-Cost Modules $$\{{2}^{n},{2}^{n}-1,{2}^{n+1}-1\}$$
• Method for Convolutional Neural Network Hardware Implementation Based on a Residue Number System

Describes a project that uses

Uses Software

• Matlab
• ImageNet
• AlexNet

This page was built for publication: Application of the residue number system to reduce hardware costs of the convolutional neural network implementation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1998097)