A storage-efficient SNN–CNN hybrid network with RRAM-implemented weights for traffic signs recognition

Y Zhang, H Xu, L Huang, C Chen - Engineering Applications of Artificial …, 2023 - Elsevier
Abstract Traffic Signs Recognition (TSR) is a key technology to implement Automatic Driving
System (ADS) and Advanced Driver Assistant System (ADAS). Numerous efforts have been …

Automatic deployment of convolutional neural networks on fpga for spaceborne remote sensing application

T Yan, N Zhang, J Li, W Liu, H Chen - Remote Sensing, 2022 - mdpi.com
In recent years, convolutional neural network (CNN)-based algorithms have been widely
used in remote sensing image processing and show tremendous performance in a variety of …

A dynamic discarding technique to increase speed and preserve accuracy for YOLOv3

I Martinez-Alpiste, G Golcarenarenji, Q Wang… - Neural Computing and …, 2021 - Springer
This paper proposes an acceleration technique to minimise the unnecessary operations on
a state-of-the-art machine learning model and thus to improve the processing speed while …

Secured convolutional layer IP core in convolutional neural network using facial biometric

A Sengupta, R Chaurasia - IEEE Transactions on Consumer …, 2022 - ieeexplore.ieee.org
This paper presents a novel methodology to design a secured custom reusable intellectual
property (IP) core for the convolutional layer of convolutional neural network (CNN). Since …

Increasing flexibility of FPGA-based CNN accelerators with dynamic partial reconfiguration

H Irmak, D Ziener, N Alachiotis - 2021 31st International …, 2021 - ieeexplore.ieee.org
Convolutional Neural Networks (CNN) are widely used for image classification and have
achieved significantly accurate performance in the last decade. However, they require …

A multilayer neural network merging image preprocessing and pattern recognition by integrating diffusion and drift memristors

Z Tang, R Zhu, R Hu, Y Chen, EQ Wu… - … on Cognitive and …, 2020 - ieeexplore.ieee.org
With the development of research on novel memristor model and device, neural networks by
integrating various memristor models have become a hot research topic recently. However …

Review of Energy-Efficient Embedded System Acceleration of Convolution Neural Networks for Organic Weeding Robots

V Czymmek, C Köhn, LO Harders, S Hussmann - Agriculture, 2023 - mdpi.com
The sustainable cultivation of organic vegetables and the associated problem of weed
control has been a current research topic for some time. Despite this, the use of chemical …

From dnns to gans: Review of efficient hardware architectures for deep learning

G Bhattacharya - arXiv preprint arXiv:2107.00092, 2021 - arxiv.org
In recent times, the trend in very large scale integration (VLSI) industry is multi-dimensional,
for example, reduction of energy consumption, occupancy of less space, precise result, less …

Bake It Till You Make It: Heat-induced Power Leakage from Masked Neural Networks

DM Mehta, M Hashemi, DS Koblah, D Forte… - Cryptology ePrint …, 2023 - eprint.iacr.org
Masking has become one of the most effective approaches for securing hardware designs
against side-channel attacks. Regardless of the effort put into correctly implementing …

Redbit: An end-to-end flexible framework for evaluating the accuracy of quantized cnns

A Santos, JD Ferreira, O Mutlu, G Falcao - arXiv preprint arXiv:2301.06193, 2023 - arxiv.org
In recent years, Convolutional Neural Networks (CNNs) have become the standard class of
deep neural network for image processing, classification and segmentation tasks. However …