Parallel and deep reservoir computing using semiconductor lasers with optical feedback

被引:28
作者
Hasegawa, Hiroshi [1 ]
Kanno, Kazutaka [1 ]
Uchida, Atsushi [1 ]
机构
[1] Saitama Univ, Dept Informat & Comp Sci, Sakura Ku, 255 Shimo Okubo, Saitama, Saitama 3388570, Japan
基金
日本学术振兴会;
关键词
deep learning; machine learning; semiconductor laser; time delay; COMPUTATION;
D O I
10.1515/nanoph-2022-0440
中图分类号
TB3 [工程材料学];
学科分类号
0805 ; 080502 ;
摘要
Photonic reservoir computing has been intensively investigated to solve machine learning tasks effectively. A simple learning procedure of output weights is used for reservoir computing. However, the lack of training of input-node and inter-node connection weights limits the performance of reservoir computing. The use of multiple reservoirs can be a solution to overcome this limitation of reservoir computing. In this study, we investigate parallel and deep configurations of delay-based all-optical reservoir computing using semiconductor lasers with optical feedback by combining multiple reservoirs to improve the performance of reservoir computing. Furthermore, we propose a hybrid configuration to maximize the benefits of parallel and deep reservoirs. We perform the chaotic time-series prediction task, nonlinear channel equalization task, and memory capacity measurement. Then, we compare the performance of single, parallel, deep, and hybrid reservoir configurations. We find that deep reservoirs are suitable for a chaotic time-series prediction task, whereas parallel reservoirs are suitable for a nonlinear channel equalization task. Hybrid reservoirs outperform other configurations for all three tasks. We further optimize the number of reservoirs for each reservoir configuration. Multiple reservoirs show great potential for the improvement of reservoir computing, which in turn can be applied for high-performance edge computing.
引用
收藏
页码:869 / 881
页数:13
相关论文
共 50 条
  • [41] Theoretical Analysis of the Optical Feedback Noise Based on Multimode Model of Semiconductor Lasers
    Imran, Sazzad M. S.
    Yamada, Minoru
    Kuwamura, Yuji
    IEEE JOURNAL OF QUANTUM ELECTRONICS, 2012, 48 (04) : 521 - 527
  • [42] Dynamics of Semiconductor Lasers with Optical Feedback from Photorefractive Phase Conjugate Mirror
    Atsushi Murakami
    Junji Ohtsubo
    Optical Review, 1999, 6 : 359 - 364
  • [43] Frequency stability and selection in semiconductor lasers by phase-conjugate optical feedback
    Khasanov, OK
    Smirnova, TV
    Fedotova, OM
    PHOTON ECHO AND COHERENT SPECTROSCOPY '97, 1997, 3239 : 216 - 220
  • [44] Distributed optical fiber vibration sensing implemented with delayed feedback reservoir computing
    Fang, Nian
    Wang, Shuai
    Wang, Chunhua
    OPTICS AND LASER TECHNOLOGY, 2023, 162
  • [45] Frequency stabilization of multiple semiconductor lasers using digital feedback loop
    Park, Paul K. J.
    Shin, S. K.
    Ji, H. C.
    Chung, Y. C.
    OPTICS COMMUNICATIONS, 2007, 272 (01) : 217 - 220
  • [46] Characteristics of chaos synchronization in semiconductor lasers subject to polarization-rotated optical feedback
    Shibasaki, N
    Uchida, A
    Yoshimori, S
    Davis, P
    IEEE JOURNAL OF QUANTUM ELECTRONICS, 2006, 42 (3-4) : 342 - 350
  • [47] Return-map for low-frequency fluctuations in semiconductor lasers with optical feedback
    Mork, J
    Sabbatier, H
    Sorensen, MP
    Tromborg, B
    OPTICS COMMUNICATIONS, 1999, 171 (1-3) : 93 - 97
  • [48] Measuring the linewidth enhancement factor of semiconductor lasers based on weak optical feedback effect
    Yu, YG
    Xi, JT
    Li, EB
    Chicharo, JF
    SEMICONDUCTOR LASERS AND APPLICATIONS II, 2004, 5628 : 34 - 39
  • [49] Performance-enhanced time-delayed photonic reservoir computing system using a reflective semiconductor optical amplifier
    Li, Xiaoyu
    Jiang, Ning
    Zhang, Qiang
    Tang, Chuanjie
    Zhang, Yiqun
    Hu, Gang
    Cao, Yongsheng
    Qiu, Kun
    OPTICS EXPRESS, 2023, 31 (18) : 28764 - 28777
  • [50] Time Delay Signature Extraction of Optical-Feedback-Induced Chaos With Reservoir Computing
    Kai, Chao
    Li, Pu
    Wang, Bingjie
    Shore, K. Alan
    Qin, Yu Wen
    Wang, Yuncai
    IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS, 2023, 29 (06)