Title :
On dimension-independent approximation by neural networks and linear approximators
Author :
Giulini, Saverio ; Sanguineti, Marcello
Author_Institution :
Sci. Dept. for Archit., Genoa Univ., Italy
Abstract :
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. The comparison is made by exhibiting families of functions belonging to suitable difference sets
Keywords :
Hilbert spaces; computational complexity; function approximation; neural nets; set theory; difference sets; dimension-independent approximation; linear approximators; multivariable functions; neural networks; Approximation error; Computer architecture; Computer networks; Electronic mail; Hilbert space; Linear approximation; Neural networks; Neurons; Polynomials; Radial basis function networks;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.857849
