Learning neural Hamiltonian dynamics: a methodological overview
The past few years have witnessed an increased interest in learning Hamiltonian dynamics
in deep learning frameworks. As an inductive bias based on physical laws, Hamiltonian …
in deep learning frameworks. As an inductive bias based on physical laws, Hamiltonian …
[HTML][HTML] Pseudo-Hamiltonian neural networks for learning partial differential equations
Pseudo-Hamiltonian neural networks (PHNN) were recently introduced for learning
dynamical systems that can be modelled by ordinary differential equations. In this paper, we …
dynamical systems that can be modelled by ordinary differential equations. In this paper, we …
Learnability of linear port-Hamiltonian systems
A complete structure-preserving learning scheme for single-input/single-output (SISO) linear
port-Hamiltonian systems is proposed. The construction is based on the solution, when …
port-Hamiltonian systems is proposed. The construction is based on the solution, when …
[HTML][HTML] Pseudo-Hamiltonian neural networks with state-dependent external forces
Hybrid machine learning based on Hamiltonian formulations has recently been successfully
demonstrated for simple mechanical systems, both energy conserving and not energy …
demonstrated for simple mechanical systems, both energy conserving and not energy …
Dynamical systems–based neural networks
Neural networks have gained much interest because of their effectiveness in many
applications. However, their mathematical properties are generally not well understood. If …
applications. However, their mathematical properties are generally not well understood. If …
Digital Battle: A Three-Layer Distributed Simulation Architecture for Heterogeneous Robot System Collaboration
J Gao, Q Liu, H Chen, H Deng, L Zhang, L Sun… - Drones, 2024 - mdpi.com
In this paper, we propose a three-layer distributed simulation network architecture, which
consists of a distributed virtual simulation network, a perception and control subnetwork, and …
consists of a distributed virtual simulation network, a perception and control subnetwork, and …
Learning dynamical systems from noisy data with inverse-explicit integrators
We introduce the mean inverse integrator (MII), a novel approach to increase the accuracy
when training neural networks to approximate vector fields of dynamical systems from noisy …
when training neural networks to approximate vector fields of dynamical systems from noisy …
Predictions based on pixel data: insights from PDEs and finite differences
Neural networks are the state-of-the-art for many approximation tasks in high-dimensional
spaces, as supported by an abundance of experimental evidence. However, we still need a …
spaces, as supported by an abundance of experimental evidence. However, we still need a …
Symplectic Neural Networks Based on Dynamical Systems
BK Tapley - arXiv preprint arXiv:2408.09821, 2024 - arxiv.org
We present and analyze a framework for designing symplectic neural networks (SympNets)
based on geometric integrators for Hamiltonian differential equations. The SympNets are …
based on geometric integrators for Hamiltonian differential equations. The SympNets are …
Power-Balanced Modeling of Nonlinear Electronic Components and Circuits for Audio Effects
J Najnudel - 2022 - theses.hal.science
This thesis is concerned with the modeling of nonlinear components and circuits for
simulations in audio applications. Our goal is to propose models that are sufficiently …
simulations in audio applications. Our goal is to propose models that are sufficiently …