On the universal approximation of real functions with varying domain

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jung, W., Morales, C. A., Tran, L. T. T.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910805777186816
author Jung, W.
Morales, C. A.
Tran, L. T. T.
author_facet Jung, W.
Morales, C. A.
Tran, L. T. T.
contents 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}.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18097
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the universal approximation of real functions with varying domain
Jung, W.
Morales, C. A.
Tran, L. T. T.
General Topology
Primary 41A65, Secondary 54C2
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}.
title On the universal approximation of real functions with varying domain
topic General Topology
Primary 41A65, Secondary 54C2
url https://arxiv.org/abs/2501.18097