Universal approximation theorem for neural networks with inputs from a topological vector space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Ismailov, Vugar
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913508393746432
author Ismailov, Vugar
author_facet Ismailov, Vugar
contents We study feedforward neural networks with inputs from a topological vector space (TVS-FNNs). Unlike traditional feedforward neural networks, TVS-FNNs can process a broader range of inputs, including sequences, matrices, functions and more. We prove a universal approximation theorem for TVS-FNNs, which demonstrates their capacity to approximate any continuous function defined on this expanded input space.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12913
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Universal approximation theorem for neural networks with inputs from a topological vector space
Ismailov, Vugar
Machine Learning
Neural and Evolutionary Computing
41A30, 41A65, 68T05
We study feedforward neural networks with inputs from a topological vector space (TVS-FNNs). Unlike traditional feedforward neural networks, TVS-FNNs can process a broader range of inputs, including sequences, matrices, functions and more. We prove a universal approximation theorem for TVS-FNNs, which demonstrates their capacity to approximate any continuous function defined on this expanded input space.
title Universal approximation theorem for neural networks with inputs from a topological vector space
topic Machine Learning
Neural and Evolutionary Computing
41A30, 41A65, 68T05
url https://arxiv.org/abs/2409.12913