Back to Search
Start Over
Measure Theoretic Results for Approximation by Neural Networks with Limited Weights.
- Source :
-
Numerical Functional Analysis & Optimization . 2017, Vol. 38 Issue 7, p819-830. 12p. - Publication Year :
- 2017
-
Abstract
- In this article, we study approximation properties of single hidden layer neural networks with weights varying in finitely many directions and with thresholds from an open interval. We obtain a necessary and simultaneously suļ¬cient 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. [ABSTRACT FROM PUBLISHER]
Details
- Language :
- English
- ISSN :
- 01630563
- Volume :
- 38
- Issue :
- 7
- Database :
- Academic Search Index
- Journal :
- Numerical Functional Analysis & Optimization
- Publication Type :
- Academic Journal
- Accession number :
- 123396120
- Full Text :
- https://doi.org/10.1080/01630563.2016.1254654