Implementation and (inverse modified) error analysis for implicitly templated ODE-nets

DOI10.1137/23M1564596MaRDI QIDQ6629683zbMATH OpenFDO

Authors Aiqing Zhu, Tom S. Bertalan, BeiBei Zhu, Yifa Tang, I. G. Kevrekidis

Publication date 30 October 2024

Published in SIAM Journal on Applied Dynamical Systems (Search for Journal in Brave)

zbMATH Keywords

deep learningimplicit schemeslearning dynamicsneural ODEsODE-nets

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Multistep, Runge-Kutta and extrapolation methods for ordinary differential equations (65L06) Approximation methods and numerical treatment of dynamical systems (37M99) Numerical solution of inverse problems involving ordinary differential equations (65L09) Numerical problems in dynamical systems (65P99)

Recommendations

• Error analysis based on inverse modified differential equations for discovery of dynamics using linear multistep methods and deep learning
• Revealing hidden dynamics from time-series data by ODENet
• An optimal control framework for adaptive neural ODEs
• Feedforward neural nets as discretization schemes for ODEs and DAEs
• PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network

Cites work

• scientific article; zbMATH DE number 88931 (Why is no real title available?)
• scientific article; zbMATH DE number 1059170 (Why is no real title available?)
• scientific article; zbMATH DE number 940566 (Why is no real title available?)
• A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms
• Algebraic structures of B-series
• Aspects of backward error analysis of numerical ODEs
• Backward Error Analysis for Numerical Integrators
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Discovery of dynamics using linear multistep methods
• GMRES: A Generalized Minimal Residual Algorithm for Solving Nonsymmetric Linear Systems
• Geometric Numerical Integration
• Hidden physics models: machine learning of nonlinear partial differential equations
• Implicit Deep Learning
• Nonparametric inference of interaction laws in systems of agents from trajectory data
• Numerical aspects for approximating governing equations using data
• Numerical integrators based on modified differential equations
• Personalized algorithm generation: a case study in learning ODE integrators
• Recent progress in the theory and application of symplectic integrators
• Revealing hidden dynamics from time-series data by ODENet
• Structure-Preserving Method for Reconstructing Unknown Hamiltonian Systems From Trajectory Data
• Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
• The discovery of dynamics via linear multistep methods and deep learning: error estimation
• The life-span of backward error analysis for numerical integrators

Cited in

(2)

• Error analysis based on inverse modified differential equations for discovery of dynamics using linear multistep methods and deep learning
• Differentiability in unrolled training of neural physics simulators on transient dynamics

This page was built for publication: Implementation and (inverse modified) error analysis for implicitly templated ODE-nets

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6629683)