In this paper, we develop a constructive theory for approximating absolutely continuous functions by series of certain sigmoidal functions. Estimates for the approximation error are also derived. The relation with neural networks approximation is discussed. The connection between sigmoidal functions and the scaling functions of (Formula presented.) -regular multiresolution approximations are investigated. In this setting, we show that the approximation error for (Formula presented.) -functions decreases as (Formula presented.) , as (Formula presented.). Examples with sigmoidal functions of several kinds, such as logistic, hyperbolic tangent, and Gompertz functions, are given.

Approximation by series of sigmoidal functions with applications to neural networks

Costarelli D.
;
2015

Abstract

In this paper, we develop a constructive theory for approximating absolutely continuous functions by series of certain sigmoidal functions. Estimates for the approximation error are also derived. The relation with neural networks approximation is discussed. The connection between sigmoidal functions and the scaling functions of (Formula presented.) -regular multiresolution approximations are investigated. In this setting, we show that the approximation error for (Formula presented.) -functions decreases as (Formula presented.) , as (Formula presented.). Examples with sigmoidal functions of several kinds, such as logistic, hyperbolic tangent, and Gompertz functions, are given.
2015
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/11391/1553542
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 36
  • ???jsp.display-item.citation.isi??? 32
social impact