Gpt-pinn: Generative pre-trained physics-informed neural networks toward non-intrusive meta-learning of parametric pdes

Y Chen, S Koohy - Finite Elements in Analysis and Design, 2024 - Elsevier
Abstract Physics-Informed Neural Network (PINN) has proven itself a powerful tool to obtain
the numerical solutions of nonlinear partial differential equations (PDEs) leveraging the …

A multi-level procedure for enhancing accuracy of machine learning algorithms

KO Lye, S Mishra, R Molinaro - European Journal of Applied …, 2021 - cambridge.org
We propose a multi-level method to increase the accuracy of machine learning algorithms
for approximating observables in scientific computing, particularly those that arise in systems …

Error analysis for deep neural network approximations of parametric hyperbolic conservation laws

T De Ryck, S Mishra - Mathematics of Computation, 2024 - ams.org
We derive rigorous bounds on the error resulting from the approximation of the solution of
parametric hyperbolic scalar conservation laws with ReLU neural networks. We show that …

On the stability and convergence of physics informed neural networks

D Gazoulis, I Gkanis, CG Makridakis - arXiv preprint arXiv:2308.05423, 2023 - arxiv.org
Physics Informed Neural Networks is a numerical method which uses neural networks to
approximate solutions of partial differential equations. It has received a lot of attention and is …

On the learning of high order polynomial reconstructions for essentially non-oscillatory schemes

VK Jayswal, RK Dubey - Physica Scripta, 2024 - iopscience.iop.org
Approximation accuracy and convergence behavior are essential required properties for the
computed numerical solution of differential equations. These requirements restrict the …

Learning WENO for entropy stable schemes to solve conservation laws

P Charles, D Ray - arXiv preprint arXiv:2403.14848, 2024 - arxiv.org
Entropy conditions play a crucial role in the extraction of a physically relevant solution for a
system of conservation laws, thus motivating the construction of entropy stable schemes that …

Eno classification and regression neural networks for numerical approximation of discontinuous flow problems

VK Jayswal, PK Pandey, RK Dubey - Soft Computing, 2024 - Springer
Learning high order non-oscillatory polynomial approximation procedures which form the
backbone of high order numerical solution of partial differential equations is challenging …

A new approach to generalisation error of machine learning algorithms: Estimates and convergence

M Loulakis, CG Makridakis - arXiv preprint arXiv:2306.13784, 2023 - arxiv.org
In this work we consider a model problem of deep neural learning, namely the learning of a
given function when it is assumed that we have access to its point values on a finite set of …

Runge-Kutta Physics Informed Neural Networks: Formulation and Analysis

G Akrivis, CG Makridakis, C Smaragdakis - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper we consider time-dependent PDEs discretized by a special class of Physics
Informed Neural Networks whose design is based on the framework of Runge--Kutta and …

On the approximation of rough functions with artificial neural networks

T De Ryck - 2020 - research-collection.ethz.ch
Deep neural networks and the ENO procedure are both efficient frameworks for
approximating rough functions. We prove that at any order, the stencil shifts of the ENO and …