Silicon-Based Metastructure Optical Scattering Multiply-Accumulate Computation Chip

被引:3
作者
Liu, Xu [1 ,2 ]
Zhu, Xudong [1 ]
Wang, Chunqing [1 ]
Cao, Yifan [1 ]
Wang, Baihang [1 ]
Ou, Hanwen [1 ]
Wu, Yizheng [1 ]
Mei, Qixun [1 ]
Zhang, Jialong [1 ]
Cong, Zhe [1 ]
Liu, Rentao [1 ]
机构
[1] Southeast Univ, Natl Res Ctr Opt Sensing Commun Integrated Networ, Dept Elect Engn, Nanjing 210096, Peoples R China
[2] State Key Lab Math Engn & Adv Comp, Wuxi 214125, Jiangsu, Peoples R China
关键词
optical neural network (ONN); multiply-accumulate (MAC) operation; inverse design; silicon-on-insulator (SOI); metastructure; coarse wavelength division multiplexer (CWDM); optical scattering unit (OSU); INVERSE DESIGN; OPTIMIZATION;
D O I
10.3390/nano12132136
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Optical neural networks (ONN) have become the most promising solution to replacing electronic neural networks, which have the advantages of large bandwidth, low energy consumption, strong parallel processing ability, and super high speed. Silicon-based micro-nano integrated photonic platforms have demonstrated good compatibility with complementary metal oxide semiconductor (CMOS) processing. Therefore, without completely changing the existing silicon-based fabrication technology, optoelectronic hybrid devices or all-optical devices of better performance can be achieved on such platforms. To meet the requirements of smaller size and higher integration for silicon photonic computing, the topology of a four-channel coarse wavelength division multiplexer (CWDM) and an optical scattering unit (OSU) are inversely designed and optimized by Lumerical software. Due to the random optical power splitting ratio and incoherency, the intensities of different input signals from CWDM can be weighted and summed directly by the subsequent OSU to accomplish arbitrary multiply-accumulate (MAC) operations, therefore supplying the core foundation for scattering ONN architecture.
引用
收藏
页数:12
相关论文
共 18 条
  • [1] [Anonymous], 2012, P 9 USENIX C NETWORK
  • [2] Bozeat RJ, 2004, TOP APPL PHYS, V94, P269
  • [3] Chih H.C, 2020, P ANSYS INNOVATION C
  • [4] Goodfellow I, 2016, ADAPT COMPUT MACH LE, P267
  • [5] Prospects and applications of photonic neural networks
    Huang, Chaoran
    Sorger, Volker J.
    Miscuglio, Mario
    Al-Qadasi, Mohammed
    Mukherjee, Avilash
    Lampe, Lutz
    Nichols, Mitchell
    Tait, Alexander N.
    Ferreira de Lima, Thomas
    Marquez, Bicky A.
    Wang, Jiahui
    Chrostowski, Lukas
    Fok, Mable P.
    Brunner, Daniel
    Fan, Shanhui
    Shekhar, Sudip
    Prucnal, Paul R.
    Shastri, Bhavin J.
    [J]. ADVANCES IN PHYSICS-X, 2022, 7 (01):
  • [6] Keraly CL, 2014, CONF LASER ELECTR
  • [7] Adjoint shape optimization applied to electromagnetic design
    Lalau-Keraly, Christopher M.
    Bhargava, Samarth
    Miller, Owen D.
    Yablonovitch, Eli
    [J]. OPTICS EXPRESS, 2013, 21 (18): : 21693 - 21701
  • [8] All-optical machine learning using diffractive deep neural networks
    Lin, Xing
    Rivenson, Yair
    Yardimei, Nezih T.
    Veli, Muhammed
    Luo, Yi
    Jarrahi, Mona
    Ozcan, Aydogan
    [J]. SCIENCE, 2018, 361 (6406) : 1004 - +
  • [9] Lin Z, 2019, INT C NUMER SIMUL, P1
  • [10] Lumea, US