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
  • [21] Learning to Swarm with Knowledge-Based Neural Ordinary Differential Equations
    Jiahao, Tom Z.
    Pan, Lishuo
    Hsieh, M. Ani
    2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2022, 2022, : 6912 - 6918
  • [22] The decomposition method for ordinary differential equations with discontinuities
    Casasús, L
    Al-Hayani, W
    APPLIED MATHEMATICS AND COMPUTATION, 2002, 131 (2-3) : 245 - 251
  • [23] DISSIPATIVE DECOMPOSITION OF ORDINARY DIFFERENTIAL-EQUATIONS
    OLVER, PJ
    SHAKIBAN, C
    PROCEEDINGS OF THE ROYAL SOCIETY OF EDINBURGH SECTION A-MATHEMATICS, 1988, 109 : 297 - 317
  • [24] Knowledge Graph Representation Learning using Ordinary Differential Equations
    Nayyeri, Mojtaba
    Xu, Chengjin
    Hoffmann, Franca
    Alam, Mirza Mohtashim
    Lehmann, Jens
    Vahdati, Sahar
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 9529 - 9548
  • [25] Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks
    Zhi, Weiming
    Lai, Tin
    Ott, Lionel
    Bonilla, Edwin V.
    Ramos, Fabio
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [26] System of Ordinary Differential Equations Solving Using Cellular Neural Networks
    Ramadan, M.
    ElDanaf, Talaat S.
    Eissa, Mahmoud A.
    JOURNAL OF ADVANCED MATHEMATICS AND APPLICATIONS, 2014, 3 (02) : 182 - 194
  • [27] Remaining Useful Life Estimation Using Neural Ordinary Differential Equations
    Star, Marco
    McKee, Kristoffer
    INTERNATIONAL JOURNAL OF PROGNOSTICS AND HEALTH MANAGEMENT, 2021, 12 (02)
  • [28] Fault Detection and Isolation for UAVs using Neural Ordinary Differential Equations
    Enciso-Salas, Luis
    Perez-Zuniga, Gustavo
    Sotomayor-Moriano, Javier
    IFAC PAPERSONLINE, 2022, 55 (06): : 643 - 648
  • [29] Heavy Ball Neural Ordinary Differential Equations
    Xia, Hedi
    Suliafu, Vai
    Ji, Hangjie
    Nguyen, Tan M.
    Bertozzi, Andrea L.
    Osher, Stanley J.
    Wang, Bao
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [30] Interpretable polynomial neural ordinary differential equations
    Fronk, Colby
    Petzold, Linda
    CHAOS, 2023, 33 (04)