Locally-symplectic neural networks for learning volume-preserving dynamics

DOI10.1016/J.JCP.2023.111911OpenAlexW4313650064MaRDI QIDQ2681119

Janis Bajars

Publication date: 10 February 2023

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

Full work available at URL: https://arxiv.org/abs/2109.09151

zbMATH Keywords

deep learningstructure preservationvolume-preserving dynamicslearning dynamical systemssymplectic neural networks

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Numerical methods for ordinary differential equations (65Lxx) Hamiltonian and Lagrangian mechanics (70Hxx)

Related Items (1)

Dynamical Systems–Based Neural Networks

Uses Software

• Adam
• NICE

Cites Work

• Unnamed Item
• Unnamed Item
• Generating functions and volume preserving mappings
• Volume-preserving algorithms for source-free dynamical systems
• Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
• Symplectic neural networks in Taylor series form for Hamiltonian systems
• A proposal on machine learning via dynamical systems
• Stable architectures for deep neural networks
• Data-Driven Science and Engineering
• Structure-preserving deep learning
• Deep Hamiltonian networks based on symplectic integrators
• Geometric Numerical Integration

This page was built for publication: Locally-symplectic neural networks for learning volume-preserving dynamics