Saved in:
Bibliographic Details
Main Author: Augustine, Midhun T
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.12895
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910532057956352
author Augustine, Midhun T
author_facet Augustine, Midhun T
contents This paper discusses various theorems on the approximation capabilities of neural networks (NNs), which are known as universal approximation theorems (UATs). The paper gives a systematic overview of UATs starting from the preliminary results on function approximation, such as Taylor's theorem, Fourier's theorem, Weierstrass approximation theorem, Kolmogorov - Arnold representation theorem, etc. Theoretical and numerical aspects of UATs are covered from both arbitrary width and depth.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12895
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Survey on Universal Approximation Theorems
Augustine, Midhun T
Machine Learning
Systems and Control
This paper discusses various theorems on the approximation capabilities of neural networks (NNs), which are known as universal approximation theorems (UATs). The paper gives a systematic overview of UATs starting from the preliminary results on function approximation, such as Taylor's theorem, Fourier's theorem, Weierstrass approximation theorem, Kolmogorov - Arnold representation theorem, etc. Theoretical and numerical aspects of UATs are covered from both arbitrary width and depth.
title A Survey on Universal Approximation Theorems
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2407.12895