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 (NNs) approximation is discussed. The connection between sigmoidal functions and the scaling functions of $r$-regular multiresolution approximations are investigated. In this setting, we show that the approximation error for $C^1$-functions decreases as $2^{-j}$, as $j \to + \infty$. Examples with sigmoidal functions of several kinds, such as logistic, hyperbolic tangent, and Gompertz functions, are given.

Costarelli, D., Spigler, R. (2015). Approximation by series of sigmoidal functions with applications to neural networks. ANNALI DI MATEMATICA PURA ED APPLICATA, 194(1), 289-306 [10.1007/s10231-013-0378-y].

Approximation by series of sigmoidal functions with applications to neural networks

SPIGLER, Renato
2015-01-01

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 (NNs) approximation is discussed. The connection between sigmoidal functions and the scaling functions of $r$-regular multiresolution approximations are investigated. In this setting, we show that the approximation error for $C^1$-functions decreases as $2^{-j}$, as $j \to + \infty$. Examples with sigmoidal functions of several kinds, such as logistic, hyperbolic tangent, and Gompertz functions, are given.
2015
Costarelli, D., Spigler, R. (2015). Approximation by series of sigmoidal functions with applications to neural networks. ANNALI DI MATEMATICA PURA ED APPLICATA, 194(1), 289-306 [10.1007/s10231-013-0378-y].
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/11590/114546
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 34
  • ???jsp.display-item.citation.isi??? 31
social impact