English

Error Estimates for Deep Learning Methods in Fluid Dynamics

Analysis of PDEs 2020-08-10 v1

Abstract

In this study, we provide error estimates and stability analysis of deep learning techniques for certain partial differential equations including the incompressible Navier-Stokes equations. In particular, we obtain explicit error estimates (in suitable norms) for the solution computed by optimizing a loss function in a Deep Neural Network (DNN) approximation of the solution, with a fixed complexity.

Keywords

Cite

@article{arxiv.2008.02844,
  title  = {Error Estimates for Deep Learning Methods in Fluid Dynamics},
  author = {Animikh Biswas and Jing Tian and Suleyman Ulusoy},
  journal= {arXiv preprint arXiv:2008.02844},
  year   = {2020}
}
R2 v1 2026-06-23T17:41:28.315Z