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
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 50 条
  • [41] The decomposition method for stiff systems of ordinary differential equations
    Mahmood, AS
    Casasús, L
    Al-Hayani, W
    APPLIED MATHEMATICS AND COMPUTATION, 2005, 167 (02) : 964 - 975
  • [42] Continuous-discrete extended Kalman filtering based on the neural ordinary differential equations method
    Zeng, Guoxu
    Chen, Shuxin
    Wu, Hao
    Yang, Mingbo
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 133
  • [43] Neural Ordinary Differential Equations for robust parameter estimation in dynamic systems with physical priors
    Yang, Yong
    Li, Haibin
    APPLIED SOFT COMPUTING, 2025, 169
  • [44] Continuous time and dynamic suicide attempt risk prediction with neural ordinary differential equations
    Sheu, Yi-han
    Simm, Jaak
    Wang, Bo
    Lee, Hyunjoon
    Smoller, Jordan W.
    NPJ DIGITAL MEDICINE, 2025, 8 (01):
  • [45] Dynamic equations on time scales and generalized ordinary differential equations
    Slavik, Antonin
    JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2012, 385 (01) : 534 - 550
  • [46] Dictionary Fields: Learning a Neural Basis Decomposition
    Chen, Anpei
    Xu, Zexiang
    Wei, Xinyue
    Tang, Siyu
    Su, Hao
    Geiger, Andreas
    ACM TRANSACTIONS ON GRAPHICS, 2023, 42 (04):
  • [47] Learning Ordinary Differential Equations for Macroeconomic Modelling
    Georgiev, Zhivko
    Kazakov, Dimitar
    2015 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2015, : 905 - 909
  • [48] Learning Thermal Properties and Temperature Models of Electric Motors with Neural Ordinary Differential Equations
    Kirchgaessner, Wilhelm
    Wallscheid, Oliver
    Bocker, Joachim
    2022 INTERNATIONAL POWER ELECTRONICS CONFERENCE (IPEC-HIMEJI 2022- ECCE ASIA), 2022, : 2746 - 2753
  • [49] A Deep Learning Neural Network Framework for Solving Singular Nonlinear Ordinary Differential Equations
    Venkatachalapathy P.
    Mallikarjunaiah S.M.
    International Journal of Applied and Computational Mathematics, 2023, 9 (5)
  • [50] Neural Ordinary Differential Equations-based Explainable Deep Learning for Process Modeling
    Wartmann, Michael R.
    Ydstie, B. Erik
    30TH EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING, PTS A-C, 2020, 48 : 1963 - 1968