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

MV Valueva, NN Nagornov, PA Lyakhov… - … and computers in …, 2020‏ - Elsevier
Convolutional neural networks are a promising tool for solving the problem of pattern
recognition. Most well-known convolutional neural networks implementations require a …

A framework for intelligence and cortical function based on grid cells in the neocortex

J Hawkins, M Lewis, M Klukas, S Purdy… - Frontiers in neural …, 2019‏ - frontiersin.org
How the neocortex works is a mystery. In this paper we propose a novel framework for
understanding its function. Grid cells are neurons in the entorhinal cortex that represent the …

Secure nearest neighbor revisited

B Yao, F Li, X **ao - … IEEE 29th international conference on data …, 2013‏ - ieeexplore.ieee.org
In this paper, we investigate the secure nearest neighbor (SNN) problem, in which a client
issues an encrypted query point E (q) to a cloud service provider and asks for an encrypted …

Privft: Private and fast text classification with homomorphic encryption

A Al Badawi, L Hoang, CF Mun, K Laine… - IEEE Access, 2020‏ - ieeexplore.ieee.org
We present an efficient and non-interactive method for Text Classification while preserving
the privacy of the content using Fully Homomorphic Encryption (FHE). Our solution (named …

Residue number systems: A new paradigm to datapath optimization for low-power and high-performance digital signal processing applications

CH Chang, AS Molahosseini… - IEEE circuits and …, 2015‏ - ieeexplore.ieee.org
Residue Number System (RNS) is a non-weighted number system which was proposed by
Garner back in 1959 to achieve fast implementation of addition, subtraction and …

Single image motion deblurring using transparency

J Jia - 2007 IEEE Conference on computer vision and pattern …, 2007‏ - ieeexplore.ieee.org
One of the key problems of restoring a degraded image from motion blur is the estimation of
the unknown shift-invariant linear blur filter. Several algorithms have been proposed using …

High-performance FV somewhat homomorphic encryption on GPUs: An implementation using CUDA

A Al Badawi, B Veeravalli, CF Mun… - IACR Transactions on …, 2018‏ - er.ceres.rub.de
Homomorphic encryption (HE) offers great capabilities that can solve a wide range of
privacy-preserving computing problems. This tool allows anyone to process encrypted data …

Research challenges in next-generation residue number system architectures

AS Molahosseini, S Sorouri… - 2012 7th international …, 2012‏ - ieeexplore.ieee.org
The carry-free nature of residue number system (RNS) has introduced it as an efficient
unconventional number system which has attracted lots of researchers for many decades …

High-performance computing based on residue number system: a review

V Balajishanmugam - 2023 9th International Conference on …, 2023‏ - ieeexplore.ieee.org
The speed of arithmetic operation is associated with the quantity of the numbers involved.
Residue Number System (RNS) is used to characterize a more significant numeral using a …

Res-DNN: A residue number system-based DNN accelerator unit

N Samimi, M Kamal, A Afzali-Kusha… - IEEE Transactions on …, 2019‏ - ieeexplore.ieee.org
In this article, a technique, based on using Residue Number System (RNS) is suggested to
improve the energy efficiency of Deep Neural Networks (DNNs). In the DNN architecture …