In the present paper, quantitative estimates for the neural network (NN) operators of the Kantorovich type, have been proved. Firstly, the modulus of continuity of the function being approximated has been used in order to estimate the approximation error in the uniform norm. Finally, a Peetre K-functional has been employed to obtain a quantitative upper bound in $L^p$-norm. At the end, several examples of sigmoidal activation functions for the above NN type operators have been provided.

Quantitative estimates involving K-functionals for neural network type operators

Danilo Costarelli
;
Gianluca Vinti
2019

Abstract

In the present paper, quantitative estimates for the neural network (NN) operators of the Kantorovich type, have been proved. Firstly, the modulus of continuity of the function being approximated has been used in order to estimate the approximation error in the uniform norm. Finally, a Peetre K-functional has been employed to obtain a quantitative upper bound in $L^p$-norm. At the end, several examples of sigmoidal activation functions for the above NN type operators have been provided.
2019
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11391/1431256
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 14
  • ???jsp.display-item.citation.isi??? 12
social impact