We study the theory of the so-called Kantorovich max-product neural network operators in the setting of Orlicz spaces $L^{arphi}$. The results here proved, extend those given by the authors in Result Math., 2016, to a more general context. The main advantage in studying neural network type operators in Orlicz spaces relies on the possibility to approximate not necessarily continuous functions (data) belonging to different function spaces by a unique general approach. Further, in order to derive quantitative estimates in this context, we introduce a suitable K-functional in $L^{arphi}$ and use it to provide an upper bound for the approximation error of the above operators. Finally, examples of sigmoidal activation functions have been considered and studied.
Approximation results in Orlicz spaces for sequences of Kantorovich max-product neural network operators
Costarelli, Danilo
Membro del Collaboration Group
;Sambucini, Anna RitaMembro del Collaboration Group
2018
Abstract
We study the theory of the so-called Kantorovich max-product neural network operators in the setting of Orlicz spaces $L^{arphi}$. The results here proved, extend those given by the authors in Result Math., 2016, to a more general context. The main advantage in studying neural network type operators in Orlicz spaces relies on the possibility to approximate not necessarily continuous functions (data) belonging to different function spaces by a unique general approach. Further, in order to derive quantitative estimates in this context, we introduce a suitable K-functional in $L^{arphi}$ and use it to provide an upper bound for the approximation error of the above operators. Finally, examples of sigmoidal activation functions have been considered and studied.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.