Saved in:
Bibliographic Details
Main Author: Monico, Chris
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.10002
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916536849006592
author Monico, Chris
author_facet Monico, Chris
contents In this short note, we give an elementary proof of a universal approximation theorem for neural networks with three hidden layers and increasing, continuous, bounded activation function. The result is weaker than the best known results, but the proof is elementary in the sense that no machinery beyond undergraduate analysis is used.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10002
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An elementary proof of a universal approximation theorem
Monico, Chris
Machine Learning
In this short note, we give an elementary proof of a universal approximation theorem for neural networks with three hidden layers and increasing, continuous, bounded activation function. The result is weaker than the best known results, but the proof is elementary in the sense that no machinery beyond undergraduate analysis is used.
title An elementary proof of a universal approximation theorem
topic Machine Learning
url https://arxiv.org/abs/2406.10002