Binary Neural Networks in FPGAs: Architectures, Tool Flows and Hardware Comparisons

Yuanxin Su; Phooi Kah; Li Minn Ang; Jeremy Smith

doi:10.3390/s23229254

Back

Binary Neural Networks in FPGAs: Architectures, Tool Flows and Hardware Comparisons

Journal article

Open access

Peer reviewed

Binary Neural Networks in FPGAs: Architectures, Tool Flows and Hardware Comparisons

Yuanxin Su, Phooi Kah, Li Minn Ang and Jeremy Smith

Sensors, Vol.23(22), pp.1-32

2023

DOI: https://doi.org/10.3390/s23229254

Files and links (1)

pdf

sensors-23-09254-v26.28 MBDownload View

Published VersionCC BY V4.0, Open Access

Abstract

Field programmable gate arrays

Neural networks

computational remodeling

binary neural network (BNN)

latency reducation

Binary neural networks (BNNs) are variations of artificial/deep neural network (ANN/DNN) architectures that constrain the real values of weights to the binary set of numbers {−1,1}. By using binary values, BNNs can convert matrix multiplications into bitwise operations, which accelerates both training and inference and reduces hardware complexity and model sizes for implementation. Compared to traditional deep learning architectures, BNNs are a good choice for implementation in resource-constrained devices like FPGAs and ASICs. However, BNNs have the disadvantage of reduced performance and accuracy because of the tradeoff due to binarization. Over the years, this has attracted the attention of the research community to overcome the performance gap of BNNs, and several architectures have been proposed. In this paper, we provide a comprehensive review of BNNs for implementation in FPGA hardware. The survey covers different aspects, such as BNN architectures and variants, design and tool flows for FPGAs, and various applications for BNNs. The final part of the paper gives some benchmark works and design tools for implementing BNNs in FPGAs based on established datasets used by the research community.

Details

Title: Binary Neural Networks in FPGAs: Architectures, Tool Flows and Hardware Comparisons
Authors: Yuanxin Su (Author) - University of Liverpool
Phooi Kah (Corresponding Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Li Minn Ang (Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Jeremy Smith (Author) - University of Liverpool
Publication details: Sensors, Vol.23(22), pp.1-32
Publisher: MDPI AG
Date published: 2023
DOI: 10.3390/s23229254
ISSN: 1424-8220
Copyright note: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Organisation Unit: School of Science, Technology and Engineering; Engage Research Lab
Language: English
Record Identifier: 99982895702621
Output Type: Journal article

Metrics

3 File views/ downloads

40 Record Views