Measure theoretic results for approximation by neural networks with limited weights
From MaRDI portal
Publication:6432064
DOI10.1080/01630563.2016.1254654zbMATH Open1373.41014arXiv2304.01880MaRDI QIDQ6432064FDOQ6432064
Authors: Vugar E. Ismailov, Ekrem Savaş 
Publication date: 4 April 2023
Abstract: In this paper, we study approximation properties of single hidden layer neural networks with weights varying on finitely many directions and thresholds from an open interval. We obtain a necessary and at the same time sufficient measure theoretic condition for density of such networks in the space of continuous functions. Further, we prove a density result for neural networks with a specifically constructed activation function and a fixed number of neurons.
Spaces of measures (46E27) Multidimensional problems (41A63) Neural networks for/in biological studies, artificial life and related topics (92B20) Spaces of measures, convergence of measures (28A33) Approximation by other special function classes (41A30)
This page was built for publication: Measure theoretic results for approximation by neural networks with limited weights
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6432064)
