气候变化领域集成服务门户(CCPortal): Inverse design of an integrated-nanophotonics optical neural network

CCPortal

DOI	10.1016/j.scib.2020.03.042
	Inverse design of an integrated-nanophotonics optical neural network
	Qu Y.; Zhu H.; Shen Y.; Zhang J.; Tao C.; Ghosh P.; Qiu M.
发表日期	2020
ISSN	20959273
起始页码	1177
结束页码	1183
卷号	65 期号:14
英文摘要	Artificial neural networks have dramatically improved the performance of many machine-learning applications such as image recognition and natural language processing. However, the electronic hardware implementations of the above-mentioned tasks are facing performance ceiling because Moore's Law is slowing down. In this article, we propose an optical neural network architecture based on optical scattering units to implement deep learning tasks with fast speed, low power consumption and small footprint. The optical scattering units allow light to scatter back and forward within a small region and can be optimized through an inverse design method. The optical scattering units can implement high-precision stochastic matrix multiplication with mean squared error <10-4 and a mere 4 × 4 μm2 footprint. Furthermore, an optical neural network framework based on optical scattering units is constructed by introducing “Kernel Matrix”, which can achieve 97.1% accuracy on the classic image classification dataset MNIST. © 2020 Science China Press
关键词	Deep learning Integrated nanophotonics Inverse design Optical neural networks Silicon photonics
英文关键词	Classification (of information); Deep learning; Design; Image enhancement; Image recognition; Inverse problems; Learning algorithms; Light scattering; Low power electronics; Matrix algebra; Mean square error; Natural language processing systems; Network architecture; Neural networks; Stochastic systems; Electronic hardwares; Inverse design methods; Low-power consumption; Machine learning applications; NAtural language processing; Optical neural networks; Optical scattering; Stochastic matrices; Forward scattering
语种	英语
来源期刊	Science Bulletin
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/207165
作者单位	Key Laboratory of 3D Micro/Nano Fabrication and Characterization of Zhejiang Province, School of Engineering, Westlake University, Hangzhou, 310024, China; Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, 310024, China; State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, 310027, China; Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139, United States; Electrical and Computer Engineering, University of California, San Diego, CA 92093, United States
推荐引用方式 GB/T 7714	Qu Y.,Zhu H.,Shen Y.,et al. Inverse design of an integrated-nanophotonics optical neural network[J],2020,65(14).
APA	Qu Y..,Zhu H..,Shen Y..,Zhang J..,Tao C..,...&Qiu M..(2020).Inverse design of an integrated-nanophotonics optical neural network.Science Bulletin,65(14).
MLA	Qu Y.,et al."Inverse design of an integrated-nanophotonics optical neural network".Science Bulletin 65.14(2020).