A time domain 2D OaA-based convolutional neural networks accelerator

A time domain 2D OaA-based convolutional neural networks accelerator

Convolutional neural networks (CNNs) are widely implemented in modern facial recognition systems for image recognition applications. Runtime speed is a critical parameter for real-time systems. Traditional FPGA-based accelerations require either large on-chip memory or high bandwidth and high memory...

Full description

Bibliographic Details
Main Authors: Rudresh Pratap Singh, Shreyam Kumar, Jugal Gandhi, Diksha Shekhawat, M. Santosh, Jai Gopal Pandey
Format: Article
Language:English
Published: Elsevier 2023-07-01
Series:Memories - Materials, Devices, Circuits and Systems
Subjects:
Convolution neural networks (CNNs)
AlexNet
VGG-16
Hardware architectures
Time domain 2D OaA
FPGA-CPU accelerators
Online Access:http://www.sciencedirect.com/science/article/pii/S277306462300018X

Internet

http://www.sciencedirect.com/science/article/pii/S277306462300018X

Similar Items