Learning robust state observers using neural odes

K Miao, K Gatsis - Learning for Dynamics and Control …, 2023 - proceedings.mlr.press
Relying on recent research results on Neural ODEs, this paper presents a methodology for
the design of state observers for nonlinear systems based on Neural ODEs, learning …

On robustness of neural ODEs image classifiers

W Cui, H Zhang, H Chu, P Hu, Y Li - Information Sciences, 2023 - Elsevier
Abstract Neural Ordinary Differential Equations (Neural ODEs), as a family of novel deep
models, delicately link conventional neural networks and dynamical systems, which bridges …

Physically consistent neural ODEs for learning multi-physics systems

M Zakwan, L Di Natale, B Svetozarevic, P Heer… - IFAC-PapersOnLine, 2023 - Elsevier
Despite the immense success of neural networks in modeling system dynamics from data,
they often remain physics-agnostic black boxes. In the particular case of physical systems …

Unconstrained parametrization of dissipative and contracting neural ordinary differential equations

D Martinelli, CL Galimberti… - 2023 62nd IEEE …, 2023 - ieeexplore.ieee.org
In this work, we introduce and study a class of Deep Neural Networks (DNNs) in continuous-
time. The proposed architecture stems from the combination of Neural Ordinary Differential …

Dynamical systems–based neural networks

E Celledoni, D Murari, B Owren, CB Schönlieb… - SIAM Journal on …, 2023 - SIAM
Neural networks have gained much interest because of their effectiveness in many
applications. However, their mathematical properties are generally not well understood. If …

Universal approximation property of Hamiltonian deep neural networks

M Zakwan, M d'Angelo… - IEEE Control Systems …, 2023 - ieeexplore.ieee.org
This letter investigates the universal approximation capabilities of Hamiltonian Deep Neural
Networks (HDNNs) that arise from the discretization of Hamiltonian Neural Ordinary …

Neural Distributed Controllers with Port-Hamiltonian Structures

M Zakwan, G Ferrari-Trecate - arxiv preprint arxiv:2403.17785, 2024 - arxiv.org
Controlling large-scale cyber-physical systems necessitates optimal distributed policies,
relying solely on local real-time data and limited communication with neighboring agents …

Neural Port-Hamiltonian Models for Nonlinear Distributed Control: An Unconstrained Parametrization Approach

M Zakwan, G Ferrari-Trecate - arxiv preprint arxiv:2411.10096, 2024 - arxiv.org
The control of large-scale cyber-physical systems requires optimal distributed policies
relying solely on limited communication with neighboring agents. However, computing …

Certifiably robust neural ode with learning-based barrier function

R Yang, R Jia, X Zhang, M ** - IEEE Control Systems Letters, 2023 - ieeexplore.ieee.org
Neural Ordinary Differential Equations (ODEs) have gained traction in many applications.
While recent studies have focused on empirically increasing the robustness of neural ODEs …

[HTML][HTML] Physics-enhanced multi-fidelity neural ordinary differential equation for forecasting long-term creep behavior of steel cables

W Zhang, SM Wang, YQ Ni, X Yuan, Y Feng… - Thin-Walled …, 2025 - Elsevier
In spatial structures, prestressed steel cables experience creep behavior when subjected to
tensile stress, resulting in stress relaxation, reduced stiffness, and potential structural failure …