Showing math.FAShow all
2 papers · 1 filter
math.FA2026
A Class of Function-Preserving Neural Network Operators with Applications to Modulated Signal Denoising
Sachin Saini
In this paper, we introduce a class of function-preserving neural network operators designed to preserve a prescribed strictly positive function. We examine the approximation behav…
math.FA2026
A Universal Approximation Theorem for Neural Networks with Outputs in Locally Convex Spaces
Sachin Saini
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 Hausdo…