Error analysis based on inverse modified differential equations for discovery of dynamics using linear multistep methods and deep learning

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

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
The life-span of backward error analysis for numerical integrators
Machine learning of linear differential equations using Gaussian processes
On the Hamiltonian interpolation of near-to-the-identity symplectic mappings with application to symplectic integration algorithms
Backward error analysis for multistep methods
Revealing hidden dynamics from time-series data by ODENet
Data driven governing equations approximation using deep neural networks
Automated reverse engineering of nonlinear dynamical systems
Backward Error Analysis for Numerical Integrators
Long-Time Energy Conservation of Numerical Methods for Oscillatory Differential Equations
Deterministic Nonperiodic Flow
Data-Driven Science and Engineering
Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth
The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation
DeepXDE: A Deep Learning Library for Solving Differential Equations
Discovery of Dynamics Using Linear Multistep Methods
Deep Network Approximation for Smooth Functions
On the Convergence of Physics Informed Neural Networks for Linear Second-Order Elliptic and Parabolic Type PDEs
Geometric Numerical Integration
Understanding Machine Learning
Dynamic systems identification with Gaussian processes
Neural network approximation
Approximation by superpositions of a sigmoidal function
On the approximation of functions by tanh neural networks

This page was built for publication: Error analysis based on inverse modified differential equations for discovery of dynamics using linear multistep methods and deep learning