Saved in:
Bibliographic Details
Main Authors: Hillebrecht, Birgit, Unger, Benjamin
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2210.03426
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Prediction error quantification in machine learning has been left out of most methodological investigations of neural networks, for both purely data-driven and physics-informed approaches. Beyond statistical investigations and generic results on the approximation capabilities of neural networks, we present a rigorous upper bound on the prediction error of physics-informed neural networks. This bound can be calculated without the knowledge of the true solution and only with a priori available information about the characteristics of the underlying dynamical system governed by a partial differential equation. We apply this a posteriori error bound exemplarily to four problems: the transport equation, the heat equation, the Navier-Stokes equation and the Klein-Gordon equation.