English

On the universal approximation of real functions with varying domain

General Topology 2025-01-31 v1

Abstract

We establish sufficient conditions for the density of shallow neural networks \cite{C89} on the family of continuous real functions defined on a compact metric space, taking into account variations in the function domains. For this we use the Gromov-Hausdorff distance defined in \cite{5G}.

Keywords

Cite

@article{arxiv.2501.18097,
  title  = {On the universal approximation of real functions with varying domain},
  author = {W. Jung and C. A. Morales and L. T. T. Tran},
  journal= {arXiv preprint arXiv:2501.18097},
  year   = {2025}
}

Comments

10 pages