Measure Theoretic Results for Approximation by Neural Networks with Limited Weights

DOI10.1080/01630563.2016.1254654zbMath1373.41014OpenAlexW2606490155MaRDI QIDQ5365276

Ekrem Savaş, Vugar E. Ismailov

Publication date: 6 October 2017

Published in: Numerical Functional Analysis and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/01630563.2016.1254654

zbMATH Keywords

weak convergenceneural networkdensityorbitBorel measureactivation functionlightning boltorthogonal measure

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Multidimensional problems (41A63) Spaces of measures, convergence of measures (28A33) Spaces of measures (46E27) Approximation by other special function classes (41A30)

Related Items (4)

On the approximation by single hidden layer feedforward neural networks with fixed weights ⋮ Approximation error of single hidden layer neural networks with fixed weights ⋮ Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions ⋮ Unnamed Item

This page was built for publication: Measure Theoretic Results for Approximation by Neural Networks with Limited Weights