Hamiltonian reduction using a convolutional auto-encoder coupled to a Hamiltonian neural network

DOI10.4208/CICP.OA-2023-0300MaRDI QIDQ6990397zbMATH OpenFDO

Authors Raphaël Côte, Emmanuel Franck, Laurent Navoret, Guillaume Steimer, Vincent Vigon

Publication date 29 April 2025

Published in Communications in Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.4208/CICP.OA-2023-0300

zbMATH Keywords

convolutional auto-encoderHamiltonian dynamicsHamiltonian neural networkmodel order reductionnonlinear wave equationsshallow water equation

Mathematics Subject Classification ID

Numerical methods for Hamiltonian systems including symplectic integrators (65P10) Artificial neural networks and deep learning (68T07)

Cites work

• A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
• A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
• A nonlinear manifold-based reduced order model for multiscale analysis of heterogeneous hyperelastic materials
• Adaptive symplectic model order reduction of parametric particle-based Vlasov–Poisson equation
• Automated discovery of generalized standard material models with EUCLID
• Deep learning
• Diffusion maps
• Dynamical reduced basis methods for Hamiltonian systems
• Geometric Numerical Integration
• Gradient-Preserving Hyper-Reduction of Nonlinear Dynamical Systems via Discrete Empirical Interpolation
• Hamiltonian reduction using a convolutional auto-encoder coupled to a Hamiltonian neural network
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Learning Eigenfunctions Links Spectral Embedding and Kernel PCA
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Non-linear manifold reduced-order models with convolutional autoencoders and reduced over-collocation method
• Nonlinear model reduction via discrete empirical interpolation
• Proper orthogonal decomposition and its applications-part. I: Theory
• Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
• Reduced basis methods for time-dependent problems
• Spectral residual method without gradient information for solving large-scale nonlinear systems of equations
• Structure-preserving model-reduction of dissipative Hamiltonian systems
• Symplectic model reduction of Hamiltonian systems
• Symplectic Model Reduction of Hamiltonian Systems on Nonlinear Manifolds and Approximation with Weakly Symplectic Autoencoder

Cited in

(2)

• Hamiltonian reduction using a convolutional auto-encoder coupled to a Hamiltonian neural network
• Neural non-canonical Hamiltonian dynamics for long-time simulations

This page was built for publication: Hamiltonian reduction using a convolutional auto-encoder coupled to a Hamiltonian neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6990397)