Extended dynamic mode decomposition with dictionary learning using neural ordinary differential equations

被引:3
作者
Terao, Hiroaki [1 ]
Shirasaka, Sho [1 ]
Suzuki, Hideyuki [1 ]
机构
[1] Osaka Univ, Grad Sch Informat Sci & Technol, 1-5 Yamadaoka, Suita, Osaka 5650871, Japan
来源
IEICE NONLINEAR THEORY AND ITS APPLICATIONS | 2021年 / 12卷 / 04期
关键词
time series analysis; Koopman operator; extended dynamic mode decomposition; machine learning; dictionary learning; neural ordinary differential equations; SYSTEMS;
D O I
10.1587/nolta.12.626
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Nonlinear phenomena can be analyzed via linear techniques using operator-theoretic approaches. Data-driven method called the extended dynamic mode decomposition (EDMD) and its variants, which approximate the Koopman operator associated with the nonlinear phenomena, have been rapidly developing by incorporating machine learning methods. Neural ordinary differential equations (NODEs), which are a neural network equipped with a continuum of layers, and have high parameter and memory efficiencies, have been proposed. In this paper, we propose an algorithm to perform EDMD using NODEs. NODEs are used to find a parameter-efficient dictionary which provides a good finite-dimensional approximation of the Koopman operator. We show the superiority of the parameter efficiency of the proposed method through numerical experiments.
引用
收藏
页码:626 / 638
页数:13
相关论文
共 25 条
  • [21] Applied Koopman operator theory for power systems technology
    Susuki, Yoshihiko
    Mezic, Igor
    Raak, Fredrik
    Hikihara, Takashi
    [J]. IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2016, 7 (04): : 430 - 459
  • [22] Takeishi N, 2017, ADV NEUR IN, V30
  • [23] Tu JH, 2014, J COMPUT DYNAM, V1, P391, DOI [10.3934/jcd.2014.1.391, DOI 10.3934/JCD.2014.1.391]
  • [24] A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
    Williams, Matthew O.
    Kevrekidis, Ioannis G.
    Rowley, Clarence W.
    [J]. JOURNAL OF NONLINEAR SCIENCE, 2015, 25 (06) : 1307 - 1346
  • [25] Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems
    Yeung, Enoch
    Kundu, Soumya
    Hodas, Nathan
    [J]. 2019 AMERICAN CONTROL CONFERENCE (ACC), 2019, : 4832 - 4839