Heavy ball neural ordinary differential equations

H Xia, V Suliafu, H Ji, T Nguyen… - Advances in …, 2021 - proceedings.neurips.cc
We propose heavy ball neural ordinary differential equations (HBNODEs), leveraging the
continuous limit of the classical momentum accelerated gradient descent, to improve neural …

On second order behaviour in augmented neural odes

A Norcliffe, C Bodnar, B Day… - Advances in neural …, 2020 - proceedings.neurips.cc
Abstract Neural Ordinary Differential Equations (NODEs) are a new class of models that
transform data continuously through infinite-depth architectures. The continuous nature of …

Experimental studies on the energy dissipation of bolted structures with frictional interfaces: A review

Y Wang, Y Ma, J Hong, G Battiato, CM Firrone - Friction, 2024 - Springer
Bolted joints play a more and more important role in the structure with lighter weight and
heavier load. This paper aims to provide an overview of different experimental approaches …

Recurrent equilibrium networks: Flexible dynamic models with guaranteed stability and robustness

M Revay, R Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
This article introduces recurrent equilibrium networks (RENs), a new class of nonlinear
dynamical models for applications in machine learning, system identification, and control …

Contraction-based methods for stable identification and robust machine learning: a tutorial

IR Manchester, M Revay… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
This tutorial paper provides an introduction to recently developed tools for machine learning,
especially learning dynamical systems (system identification), with stability and robustness …

Good practices for designing and experimental testing of dynamically excited jointed structures: The Orion beam

RO Teloli, P Butaud, G Chevallier, S da Silva - Mechanical Systems and …, 2022 - Elsevier
This paper proposes a new lap-joint configuration, the so-called Orion beam. The new setup
is composed of two thin beams connected by three bolted joints with contact patches on …

Recurrent equilibrium networks: Unconstrained learning of stable and robust dynamical models

M Revay, R Wang… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
This paper introduces recurrent equilibrium networks (RENs), a new class of nonlinear
dynamical models for applications in machine learning and system identification. The new …

Mechanistic neural networks for scientific machine learning

A Pervez, F Locatello, E Gavves - arXiv preprint arXiv:2402.13077, 2024 - arxiv.org
This paper presents Mechanistic Neural Networks, a neural network design for machine
learning applications in the sciences. It incorporates a new Mechanistic Block in standard …

Reducing black-box nonlinear state-space models: a real-life case study

PZ Csurcsia, J Decuyper, B Renczes… - … Systems and Signal …, 2024 - Elsevier
A known challenge when building nonlinear models from data is to limit the size of the
model in terms of the number of parameters. Especially for complex nonlinear systems …

Non-parametric identification of multivariable systems: A local rational modeling approach with application to a vibration isolation benchmark

R Voorhoeve, A van der Maas, T Oomen - Mechanical Systems and Signal …, 2018 - Elsevier
Frequency response function (FRF) identification is often used as a basis for control systems
design and as a starting point for subsequent parametric system identification. The aim of …