On Dimension-Independent Approximation by Neural Networks and Linear Approximators
- Giulini, Saverio
- Sanguineti, Marcello
Publication date
January 2000
DOI Publisher
Institute of Electrical and Electronics Engineers (IEEE)Abstract
Sets of multivariable functions that can be approximated with \u201cdimension-independent\u201d rates either by linear approximators or by neural networks having various types of computational units are compared. The comparison is made by exhibiting families of functions belonging to suitable difference set
Add to ORKG