Reservoir computing with noise

被引:8
|
作者
Nathe, Chad [1 ]
Pappu, Chandra [2 ]
Mecholsky, Nicholas A. [3 ]
Hart, Joe [4 ]
Carroll, Thomas [4 ]
Sorrentino, Francesco [1 ]
机构
[1] Univ New Mexico, Mech Engn Dept, Albuquerque, NM 87131 USA
[2] Union Coll, Elect Comp & Biomed Engn Dept, Schenectady, NY 12309 USA
[3] Catholic Univ Amer, Dept Phys, Vitreous State Lab, Washington, DC 20064 USA
[4] US Naval Res Lab, Washington, DC 20375 USA
基金
美国国家卫生研究院;
关键词
D O I
10.1063/5.0130278
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
This paper investigates in detail the effects of measurement noise on the performance of reservoir computing. We focus on an application in which reservoir computers are used to learn the relationship between different state variables of a chaotic system. We recognize that noise can affect the training and testing phases differently. We find that the best performance of the reservoir is achieved when the strength of the noise that affects the input signal in the training phase equals the strength of the noise that affects the input signal in the testing phase. For all the cases we examined, we found that a good remedy to noise is to low-pass filter the input and the training/testing signals; this typically preserves the performance of the reservoir, while reducing the undesired effects of noise.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Taking advantage of noise in quantum reservoir computing
    Domingo, L.
    Carlo, G.
    Borondo, F.
    SCIENTIFIC REPORTS, 2023, 13 (01)
  • [2] Taking advantage of noise in quantum reservoir computing
    L. Domingo
    G. Carlo
    F. Borondo
    Scientific Reports, 13
  • [3] Performance improvement of in-materio reservoir computing by noise injection
    Hakoshima, Masaya
    Usami, Yuki
    Kotooka, Takumi
    Tanaka, Hirofumi
    JAPANESE JOURNAL OF APPLIED PHYSICS, 2023, 62 (SG)
  • [4] Optoelectronic reservoir computing: tackling noise-induced performance degradation
    Soriano, M. C.
    Ortin, S.
    Brunner, D.
    Larger, L.
    Mirasso, C. R.
    Fischer, I.
    Pesquera, L.
    OPTICS EXPRESS, 2013, 21 (01): : 12 - 20
  • [5] Noise sensitivity of physical reservoir computing in a ring array of atomic switches
    Kubota, Hiroshi
    Hasegawa, Tsuyoshi
    Akai-Kasaya, Megumi
    Asai, Tetsuya
    IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2022, 13 (02): : 373 - 378
  • [6] Noise effects on time delay reservoir computing using silicon microring resonators
    Donati, Giovanni
    Argyris, Apostolos
    Mirasso, Claudio R.
    Mancinelli, Mattia
    Pavesi, Lorenzo
    INTEGRATED OPTICS: DEVICES, MATERIALS, AND TECHNOLOGIES XXVI, 2022, 12004
  • [7] Towards Using Reservoir Computing Networks for Noise-Robust Image Recognition
    Jalalvand, Azarakhsh
    De Neve, Wesley
    Van de Walle, Rik
    Martens, Jean-Pierre
    2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 1666 - 1672
  • [8] Noise Robust Reservoir Computing Based on Flexible Doped Hafnium Oxide Memcapacitors
    Xing, Qianye
    Pei, Mengjiao
    Qiao, Lesheng
    Peng, Baocheng
    Shi, Kailu
    Fang, Xiao
    Cui, Hangyuan
    Wan, Changjin
    Wan, Qing
    IEEE TRANSACTIONS ON ELECTRON DEVICES, 2024, 71 (05) : 2970 - 2975
  • [9] Learning noise-induced transitions by multi-scaling reservoir computing
    Lin, Zequn
    Lu, Zhaofan
    Di, Zengru
    Tang, Ying
    NATURE COMMUNICATIONS, 2024, 15 (01)
  • [10] A reservoir computing approach for molecular computing
    Yahiro, Wataru
    Aubert-Kato, Nathanael
    Hagiya, Masami
    2018 CONFERENCE ON ARTIFICIAL LIFE (ALIFE 2018), 2018, : 31 - 38