Work

Universal approximation results for neural networks with non-polynomial activation function over non-compact domains

Year: 2025

Type: article

Abstract: This paper extends the universal approximation property of single-hidden-layer feedforward neural networks beyond compact domains, which is of particular interest for the approximation within weighted [Formula: see text]-spaces and weighted Sobolev spaces over unbounded domains. More precisely, by assuming that the activation function is non-polynomial, we establish universal approximation results within function spaces defined over non-compact subsets of a Euclidean space, including [Formula: see text]-spaces, weighted [Formula: see text]-spaces, and weighted Sobolev spaces, where the latter two include the approximation of the (weak) derivatives. Moreover, we provide some dimension-independent rates for approximating a function with sufficiently regular and integrable Fourier transform by neural networks with non-polynomial activation function.

Source: Analysis and Applications

DOI: 10.1142/s0219530525500423

Authors: Ariel Neufeld, Philipp Schmocker

Institution: Nanyang Technological University

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Ministry of Education - Singapore, Nanyang Technological University, Ministry of Education, India

Award: G3208415180