Symplectic learning for Hamiltonian neural networks

DOI10.1016/J.JCP.2023.112495arXiv2106.11753OpenAlexW3173623556MaRDI QIDQ6087912

Marco David, Florian Méhats

Publication date: 16 November 2023

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.11753

zbMATH Keywords

ordinary differential equationHamiltonian systemgeometric numerical integrationsymplectic numerical methodHamiltonian neural network

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Numerical methods for ordinary differential equations (65Lxx) Numerical problems in dynamical systems (65Pxx)

Related Items (2)

Pseudo-Hamiltonian system identification ⋮ Learning Hamiltonian systems with mono-implicit Runge-Kutta methods

Cites Work

• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• A family of embedded Runge-Kutta formulae
• Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
• Symplectic neural networks in Taylor series form for Hamiltonian systems
• Signed particles and neural networks, towards efficient simulations of quantum systems
• Machine learning for fast and reliable solution of time-dependent differential equations
• Machine Learning for Fluid Mechanics
• Numerical integrators based on modified differential equations
• Classical Mechanics
• Deep Hamiltonian networks based on symplectic integrators
• Deep Network Approximation for Smooth Functions
• Geometric Numerical Integration
• Deep learning for physical processes: incorporating prior scientific knowledge
• On the approximation of functions by tanh neural networks

This page was built for publication: Symplectic learning for Hamiltonian neural networks