IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1
On Dimension-Independent Approximation by Neural Networks and Linear Approximators
Como, Italy
July 24-July 27
ISBN: 0-7695-0619-4
Sets of multivariable functions that can be approximated with “dimension-independent” rates either by linear approximators or by neural networks having various types of computational units are compared. Exhibiting families of functions belonging to suitable difference sets make the comparison.
Index Terms:
dimension-independent approximation, neural networks, complexity, Kolmogorov n-width
Citation:
Saverio Giulini, Marcello Sanguineti, "On Dimension-Independent Approximation by Neural Networks and Linear Approximators," ijcnn, vol. 1, pp.1283, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 1, 2000