Efficient hardware architectures for accelerating deep neural networks: Survey

P Dhilleswararao, S Boppu, MS Manikandan… - IEEE …, 2022 - ieeexplore.ieee.org
In the modern-day era of technology, a paradigm shift has been witnessed in the areas
involving applications of Artificial Intelligence (AI), Machine Learning (ML), and Deep …

Suitability of recent hardware accelerators (DSPs, FPGAs, and GPUs) for computer vision and image processing algorithms

A HajiRassouliha, AJ Taberner, MP Nash… - Signal Processing …, 2018 - Elsevier
Computer vision and image processing algorithms form essential components of many
industrial, medical, commercial, and research-related applications. Modern imaging systems …

Quantized neural networks: Training neural networks with low precision weights and activations

I Hubara, M Courbariaux, D Soudry, R El-Yaniv… - Journal of Machine …, 2018 - jmlr.org
The principal submatrix localization problem deals with recovering a K× K principal
submatrix of elevated mean µ in a large n× n symmetric matrix subject to additive standard …

Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients

S Zhou, Y Wu, Z Ni, X Zhou, H Wen, Y Zou - arXiv preprint arXiv …, 2016 - arxiv.org
We propose DoReFa-Net, a method to train convolutional neural networks that have low
bitwidth weights and activations using low bitwidth parameter gradients. In particular, during …

ISAAC: A convolutional neural network accelerator with in-situ analog arithmetic in crossbars

A Shafiee, A Nag, N Muralimanohar… - ACM SIGARCH …, 2016 - dl.acm.org
A number of recent efforts have attempted to design accelerators for popular machine
learning algorithms, such as those involving convolutional and deep neural networks (CNNs …

Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1

M Courbariaux, I Hubara, D Soudry, R El-Yaniv… - arXiv preprint arXiv …, 2016 - arxiv.org
We introduce a method to train Binarized Neural Networks (BNNs)-neural networks with
binary weights and activations at run-time. At training-time the binary weights and activations …

[图书][B] Deep learning

I Goodfellow, Y Bengio, A Courville - 2016 - books.google.com
An introduction to a broad range of topics in deep learning, covering mathematical and
conceptual background, deep learning techniques used in industry, and research …

Hardware implementation of deep network accelerators towards healthcare and biomedical applications

MR Azghadi, C Lammie, JK Eshraghian… - … Circuits and Systems, 2020 - ieeexplore.ieee.org
The advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors
has brought on new opportunities for applying both Deep and Spiking Neural Network …

Memory and information processing in neuromorphic systems

G Indiveri, SC Liu - Proceedings of the IEEE, 2015 - ieeexplore.ieee.org
A striking difference between brain-inspired neuromorphic processors and current von
Neumann processor architectures is the way in which memory and processing is organized …

[图书][B] Deep learning

Y Bengio, I Goodfellow, A Courville - 2017 - academia.edu
Inventors have long dreamed of creating machines that think. Ancient Greek myths tell of
intelligent objects, such as animated statues of human beings and tables that arrive full of …