Hardware implementations of computer-generated holography: a review

Y Wang, D Dong, PJ Christopher, A Kadis… - Optical …, 2020 - spiedigitallibrary.org
Computer-generated holography (CGH) is a technique to generate holographic interference
patterns. One of the major issues related to computer hologram generation is the massive …

Edge compression: An integrated framework for compressive imaging processing on cavs

S Lu, X Yuan, W Shi - 2020 IEEE/ACM Symposium on Edge …, 2020 - ieeexplore.ieee.org
Machine vision is the key to the successful deployment of many Advanced Driver Assistant
System (ADAS)/Automated Driving System (ADS) functions, which require accurate high …

Accelerating transformer neural networks on fpgas for high energy physics experiments

F Wojcicki, Z Que, AD Tapper… - … Conference on Field …, 2022 - ieeexplore.ieee.org
High Energy Physics studies the fundamental forces and elementary particles of the
Universe. With the unprecedented scale of experiments comes the challenge of accurate …

Qtorch+: next generation arithmetic for Pytorch machine learning

NM Ho, H De Silva, JL Gustafson, WF Wong - Conference on Next …, 2022 - Springer
This paper presents Qtorch+, a tool which enables next generation number formats on
Pytorch, a widely popular high-level Deep Learning framework. With hand-crafted GPU …

Hardware designs for convolutional neural networks: Memoryful, memoryless and cached

ABZ de França, FDVR Oliveira, JGRC Gomes… - Integration, 2024 - Elsevier
This work presents three hardware architectures for convolutional neural networks with high
degree of parallelism and component reuse implemented in a programmable device. The …

Power and area efficient cascaded effectless GDI approximate adder for accelerating multimedia applications using deep learning model

M Nagarajan, R Muthaiah… - Computational …, 2022 - Wiley Online Library
Approximate computing is an upsurging technique to accelerate the process through less
computational effort while keeping admissible accuracy of error‐tolerant applications such …

A low-cost in-tire-pressure monitoring SoC using integer/floating-point type convolutional neural network inference engine

A Vasantharaj, SA Karuppusamy… - Microprocessors and …, 2023 - Elsevier
Tire pressure state is crucial for driving performance and fuel efficiency and is the welfare of
the driver. Tire inflation pressure greatly affects fuel consumption, driving dynamics and the …

Deep learning and robotics, surgical robot applications

MS Iqbal, R Abbasi, W Ahmad, FS Akbar - Artificial Intelligence for …, 2023 - Springer
Surgical robots can perform difficult tasks that humans cannot. They can perform repetitive
tasks, work with hazardous materials, and can operate difficult objects. This has helped …

Design and Implementation of OpenCL-Based FPGA Accelerator for YOLOv2

C Cui, F Ge, Z Li, X Yue, F Zhou… - 2021 IEEE 21st …, 2021 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) are widely used in practical scenarios such as
license plate recognition, face recognition and radar image detection, where the main …

LOCOFloat: A low-cost floating-point format for FPGAs.: Application to HIL simulators

A Sanchez, A de Castro, MS Martínez-García, J Garrido - Electronics, 2020 - mdpi.com
One of the main decisions when making a digital design is which arithmetic is going to be
used. The arithmetic determines the hardware resources needed and the latency of every …