A General Constructive Upper Bound on Shallow Neural Nets Complexity
Machine Learning
2025-10-09 v1 Machine Learning
Abstract
We provide an upper bound on the number of neurons required in a shallow neural network to approximate a continuous function on a compact set with a given accuracy. This method, inspired by a specific proof of the Stone-Weierstrass theorem, is constructive and more general than previous bounds of this character, as it applies to any continuous function on any compact set.
Cite
@article{arxiv.2510.06372,
title = {A General Constructive Upper Bound on Shallow Neural Nets Complexity},
author = {Frantisek Hakl and Vit Fojtik},
journal= {arXiv preprint arXiv:2510.06372},
year = {2025}
}