paper

An elementary proof of a universal approximation theorem

arXiv:2406.10002

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.

Added some additional clarification at several points in the arguments

An elementary proof of a universal approximation theorem · wovepaper