IEICE Transactions on Electronics最新文献_第9页

A High-Speed PWM-Modulated Transceiver Network for Closed-Loop Channel Topology 一种用于闭环信道拓扑的高速pwm调制收发器网络

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2020-01-01 DOI: 10.1587/transele.2020cds0001

Kyong-Taek Lee, J. Sim

引用次数: 0

SLIT: An Energy-Efficient Reconfigurable Hardware Architecture for Deep Convolutional Neural Networks 深度卷积神经网络的高效可重构硬件结构

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2020-01-01 DOI: 10.1587/transele.2020cdp0002

Thi Diem Tran, Y. Nakashima

{"title":"SLIT: An Energy-Efficient Reconfigurable Hardware Architecture for Deep Convolutional Neural Networks","authors":"Thi Diem Tran, Y. Nakashima","doi":"10.1587/transele.2020cdp0002","DOIUrl":"https://doi.org/10.1587/transele.2020cdp0002","url":null,"abstract":"Convolutional neural networks (CNNs) have dominated a range of applications, from advanced manufacturing to autonomous cars. For energy cost-efficiency, developing low-power hardware for CNNs is a research trend. Due to the large input size, the first few convolutional layers generally consume most latency and hardware resources on hardware design. To address these challenges, this paper proposes an innovative architecture named SLIT to extract feature maps and reconstruct the first few layers on CNNs. In this reconstruction approach, total multiplyaccumulate operations are eliminated on the first layers. We evaluate new topology with MNIST, CIFAR, SVHN, and ImageNet datasets on image classification application. Latency and hardware resources of the inference step are evaluated on the chip ZC7Z020-1CLG484C FPGA with Lenet-5 and VGG schemes. On the Lenet-5 scheme, our architecture reduces 39% of latency and 70% of hardware resources with a 0.456 W power consumption compared to previous works. Even though the VGG models perform with a 10% reduction in hardware resources and latency, we hope our overall results will potentially give a new impetus for future studies to reach a higher optimization on hardware design. Notably, the SLIT architecture efficiently merges with most popular CNNs at a slightly sacrificing accuracy of a factor of 0.27% on MNIST, ranging from 0.5% to 1.5% on CIFAR, approximately 2.2% on ImageNet, and remaining the same on SVHN databases. key words: primary visual cortex, image classification, convolutional neural network, hardware architecture, FPGA, feature extraction","PeriodicalId":50384,"journal":{"name":"IEICE Transactions on Electronics","volume":null,"pages":null},"PeriodicalIF":0.5,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67305912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-11-01 DOI: 10.1587/transele.2019dif0001

H. Kominami

引用次数: 0

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-10-01 DOI: 10.1587/transele.2019mmf0001

Atsushi Sanada

引用次数: 0

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-09-01 DOI: 10.1587/transele.2019emf0001

Y. Abe

引用次数: 0

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-07-01 DOI: 10.1587/transele.2018ctf0001

Masao Ito

引用次数: 0

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-06-01 DOI: 10.1587/transele.2018fuf0001

Kunio Tsuda

引用次数: 0

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-04-01 DOI: 10.1587/transele.2018odf0001

Tsuyoshi Yamamoto

引用次数: 0

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-04-01 DOI: 10.1587/transele.2018cdf0001

Hideto Hidaka

引用次数: 0

FOREWORD 前言

IF 0.5 4区工程技术

IEICE Transactions on Electronics Pub Date : 2019-03-01 DOI: 10.1587/transele.2018sdf0001

M. Hidaka

引用次数: 0