An elementary proof of a universal approximation theorem
Machine Learning
2024-12-24 v2
Abstract
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.
Cite
@article{arxiv.2406.10002,
title = {An elementary proof of a universal approximation theorem},
author = {Chris Monico},
journal= {arXiv preprint arXiv:2406.10002},
year = {2024}
}
Comments
Added some additional clarification at several points in the arguments