Photonic perceptron based on a Kerr microcomb for high-speed, scalable, optical neural networks

被引:0
|
作者
Xu, Xingyuan [1 ,2 ]
Tan, Mengxi [1 ]
Wu, Jiayang [1 ]
Boes, Andreas [3 ]
Corcoran, Bill [2 ]
Nguyen, Thach G. [3 ]
Chu, Sai T. [4 ]
Little, Brent E. [5 ]
Morandotti, Roberto [6 ]
Mitchell, Arnan [3 ]
Hicks, Damien G. [1 ,7 ]
Moss, David J. [1 ]
机构
[1] Swinburne Univ Technol, Opt Sci Ctr, Hawthorn, Vic 3122, Australia
[2] Monash Univ, Dept Elect & Comp Syst Engn, Clayton, Vic 3800, Australia
[3] RMIT Univ, Sch Engn, Melbourne, Vic 3001, Australia
[4] City Univ Hong Kong, Dept Phys & Mat Sci, Tat Chee Ave, Hong Kong, Peoples R China
[5] Chinese Acad Sci, Xian Inst Opt & Precis Mech Precis Mech, Xian, Peoples R China
[6] INRS Energie Mat & Telecommun, 1650 Blvd Lionel Boulet, Varennes, PQ J3X 1S2, Canada
[7] Walter & Eliza Hall Inst Med Res, Bioinformat Div, Parkville, Vic 3052, Australia
关键词
WAVELENGTH CONVERSION; HILBERT TRANSFORMER; TUNABLE DISPERSION; COMB; MICROWAVE; RF; FILTER; LASER; GENERATION;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Optical artificial neural networks (ONNs) have significant potential for ultra-high computing speed and energy efficiency. We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds, demonstrating the building block of the ONN - a single neuron perceptron - by mapping synapses onto 49 wavelengths to achieve a single-unit throughput of 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We test the perceptron on handwritten-digit recognition and cancer-cell detection - achieving over 90% and 85% accuracy, respectively. By scaling the perceptron to a deep learning network using off-the-shelf telecom technology we can achieve high throughput operation for matrix multiplication for real-time massive data processing.
引用
收藏
页码:220 / 224
页数:5
相关论文
共 50 条
  • [42] High-Speed Optical Devices for Data Center Networks
    Tanaka, Shigehisa
    Suzuki, Takanori
    Adachi, Koichiro
    Nakahara, Kouji
    2018 IEEE CPMT SYMPOSIUM JAPAN (ICSJ), 2018, : 19 - 20
  • [43] Optical rate conversion for high-speed TDM networks
    Patel, NS
    Hall, KL
    Rauschenbach, KA
    IEEE PHOTONICS TECHNOLOGY LETTERS, 1997, 9 (09) : 1277 - 1279
  • [44] High-speed avionic optical fiber CDMA networks
    Zhang, JG
    IEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE, 1999, 14 (06) : 15 - 21
  • [45] High-speed avionic optical fiber CDMA networks
    Telecommunications Program, School of Advanced Technologies, Asian Institute of Technology, P.O. Box 4, Klong Luang, Pathumthani 12120, Thailand
    IEEE Aerosp Electron Syst Mag, 6 (15-21):
  • [46] Efficient Rijndael implementation for high-speed optical networks
    Rejeb, J
    Ramaswamy, V
    ICT'2003: 10TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS, VOLS I AND II, CONFERENCE PROCEEDINGS, 2003, : 641 - 645
  • [47] OPTICAL SOLITON COMMUNICATION TECHNOLOGIES FOR HIGH-SPEED NETWORKS
    NAKAZAWA, M
    NTT REVIEW, 1994, 6 (01): : 71 - 77
  • [48] High-speed optical transmission system for backbone networks
    Sakai, Kazutaka
    Yamamoto, Kagehiro
    Taima, Kiichirou
    Ishikawa, Ichirou
    Hitachi Review, 2000, 49 (04): : 163 - 167
  • [49] High-speed digital optical processing in future networks
    Cotter, D
    Lucek, JK
    PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY OF LONDON SERIES A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2000, 358 (1773): : 2283 - 2296
  • [50] Optical TDM sorting networks for high-speed switching
    Univ of Michigan-Dearborn, Dearborn, United States
    IEEE Trans Commun, 6 (723-736):