DeepAI AI Chat
Log In Sign Up

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

by   Hiroaki Terao, et al.
Osaka University

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.


page 11

page 13


Numerical methods to evaluate Koopman matrix from system equations

A method that is employed to evaluate a Koopman matrix from a data set o...

Parameter-varying neural ordinary differential equations with partition-of-unity networks

In this study, we propose parameter-varying neural ordinary differential...

Adaptive semiparametric Bayesian differential equations via sequential Monte Carlo

Nonlinear differential equations (DEs) are used in a wide range of scien...

Data-Driven Encoding: A New Numerical Method for Computation of the Koopman Operator

This paper presents a data-driven method for constructing a Koopman line...

Heterogeneous mixtures of dictionary functions to approximate subspace invariance in Koopman operators

Koopman operators model nonlinear dynamics as a linear dynamic system ac...

Forecasting emissions through Kaya identity using Neural Ordinary Differential Equations

Starting from the Kaya identity, we used a Neural ODE model to predict t...