A Universal Approximation Theorem for Neural Networks with Outputs in Locally Convex Spaces

TL;DR

This paper proves a universal approximation theorem for shallow neural networks with inputs in topological vector spaces and outputs in locally convex spaces, extending classical scalar-valued results to more general settings.

Contribution

It establishes a universal approximation theorem for neural networks with outputs in locally convex spaces, generalizing previous scalar-valued theorems to broader topological vector space contexts.

Findings

Neural networks are dense in continuous mappings between certain topological vector spaces.

The theorem extends classical scalar-valued approximation results to Banach and Hilbert spaces.

Applications include operator approximation between function spaces.

Abstract

In this paper, a universal approximation theorem (UAT) for shallow neural networks whose inputs belong to a topological vector space (TVS) and whose outputs take values in a Hausdorff locally convex TVS is established. The networks are constructed using scalar activation functions applied to continuous linear functionals of the input, while the output coefficients lie in the target space. It is shown that this class of neural networks is dense in the space of continuous mappings from a compact subset of the input space into the target space with respect to the topology of uniform convergence induced by the defining seminorms. The result extends existing scalar-valued approximation theorems on TVS and includes Banach and Hilbert-valued approximation as special cases. Several corollaries and examples are provided, illustrating applications to operator approximation between function spaces.