arrow
返回

Microcomb-based integrated photonic processing unit

delete2023-01-05
delete107
delete
OA
AI
B
Bai, Bowen
Q
Qipeng Yang
S
Shu, Haowen
C
Chang, Lin
Y
Yang, Fenghe
S
Shen, Bitao
Z
Zihan Tao
W
Wang, Jing
徐
徐绍夫 (Shaofu Xu)
X
Xie, Weiqiang
Z
Zou, Weiwen
H
Hu, Weiwei
B
Bowers, John E. E. *
W
Wang, Xingjun *
DOI:10.1038/s41467-022-35506-9delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Optical neural networks face remarkable challenges in high-level integration and on-chip operation. In this work the authors enable optical convolution utilizing time-wavelength plane stretching approach on a microcomb-driven chip-based photonic processing unit. The emergence of parallel convolution-operation technology has substantially powered the complexity and functionality of optical neural networks (ONN) by harnessing the dimension of optical wavelength. However, this advanced architecture faces remarkable challenges in high-level integration and on-chip operation. In this work, convolution based on time-wavelength plane stretching approach is implemented on a microcomb-driven chip-based photonic processing unit (PPU). To support the operation of this processing unit, we develop a dedicated control and operation protocol, leading to a record high weight precision of 9 bits. Moreover, the compact architecture and high data loading speed enable a preeminent photonic-core compute density of over 1 trillion of operations per second per square millimeter (TOPS mm(-2)). Two proof-of-concept experiments are demonstrated, including image edge detection and handwritten digit recognition, showing comparable processing capability compared to that of a digital computer. Due to the advanced performance and the great scalability, this parallel photonic processing unit can potentially revolutionize sophisticated artificial intelligence tasks including autonomous driving, video action recognition and image reconstruction.
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Nature Communications 封面图
Nature Communications
IF:
15.7
论文数:
9.4W
被引数:
91.2W

机构

P
peking university
学者数:
11.9W
论文数: 8.7W
被引数: 146
University of California System 封面图
University of California System
学者数:
37.7W
论文数: 33.8W
被引数: 6.6K
Z
Zhangjiang Laboratory
学者数:
548
论文数: 395
被引数: 2
学者 查看更多机构
引用论文

引用论文

True fractional calcium absorption in Chinese children measured with stable isotopes (42Ca and44Ca)
err2007-03-09
err0
errOAAI
errWarren T.L. Lee; Sophie S.F. Leung; Susan J.Fairweather-Tait; Dora M.Y. Leung; Heidi S.Y. Tsang; John Eagles; Tom Fox; S.H. Wang; Y.C. Xu; W.P. Zeng; Joseph Lau; J.R.L. Masarei
err分享
err收藏
Photonics for artificial intelligence and neuromorphic computing用于人工智能和神经形态计算的光子学
err2021-01-29
err995
errOAAI
errShastri, Bhavin J.; Tait, Alexander N.; de Lima, T. Ferreira; Pernice, Wolfram H. P.; Bhaskaran, Harish; Wright, C. D.; Prucnal, Paul R.
err分享
err收藏
An all-optical neuron with sigmoid activation function
err2019-03-20
err169
errOAAI
errMourgias-Alexandris, G.; Tsakyridis, A.; Passalis, N.; Tefas, A.; Vyrsokinos, K.; Pleros, N.
err分享
err收藏
Heterogeneous Silicon/III-V Semiconductor Optical Amplifiers
err2016-11-01
err111
errOAAI
errDavenport, Michael L.; Skendzic, Sandra; Volet, Nicolas; Hulme, Jared C.; Heck, Martijn J. R.; Bowers, John E.
err分享
err收藏
International Standards for Neurological and Functional Classification of Spinal Cord Injury
err1997-05-01
err0
errOAAI
errFrederick M Maynard; Michael B Bracken; Graham Creasey; John F Ditunno Jr; William H Donovan; Thomas B Ducker; Susan L Garber; Ralph J Marino; Samuel L Stover; Charles H Tator; Robert L Waters; Jack E Wilberger; Wise Young
err分享
err收藏
err分享
err收藏
Hertz-linewidth semiconductor lasers using CMOS-ready ultra-high-Q microresonators使用CMOS就绪的超高Q微谐振器的赫兹线宽半导体激光器
err2021-02-11
err363
errOAAI
errJin, Warren; Yang, Qi-Fan; Chang, Lin; Shen, Boqiang; Wang, Heming; Leal, Mark A.; Wu, Lue; Gao, Maodong; Feshali, Avi; Paniccia, Mario; Vahala, Kerry J.; Bowers, John E.
err分享
err收藏
学者 查看更多内容