VPNets: volume-preserving neural networks for learning source-free dynamics

DOI10.1016/j.cam.2022.114523OpenAlexW4225301074WikidataQ114952701 ScholiaQ114952701MaRDI QIDQ2161067

Jia-Wei Zhang, Jian Liu, Aiqing Zhu, Yi-Fa Tang, BeiBei Zhu

Publication date: 4 August 2022

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2204.13843

zbMATH Keywords

neural networksdeep learningvolume-preservingdiscovery of dynamicssource-free dynamics

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Identification in stochastic control theory (93E12) Multistep, Runge-Kutta and extrapolation methods for ordinary differential equations (65L06) Time series analysis of dynamical systems (37M10) Numerical methods for Hamiltonian systems including symplectic integrators (65P10)

Uses Software

• Adam
• NICE
• torchdiffeq
• DeepONet

Cites Work

• Machine learning of linear differential equations using Gaussian processes
• Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
• Symplectic neural networks in Taylor series form for Hamiltonian systems
• Data driven governing equations approximation using deep neural networks
• Automated reverse engineering of nonlinear dynamical systems
• Structure-preserving deep learning
• Unit Triangular Factorization of the Matrix Symplectic Group
• Structure-Preserving Method for Reconstructing Unknown Hamiltonian Systems From Trajectory Data
• Discovery of Dynamics Using Linear Multistep Methods
• Geometric Numerical Integration
• Dynamic systems identification with Gaussian processes
• Approximation by superpositions of a sigmoidal function

This page was built for publication: VPNets: volume-preserving neural networks for learning source-free dynamics