On the approximation by single hidden layer feedforward neural networks with fixed weights - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Neural Networks Année : 2018

On the approximation by single hidden layer feedforward neural networks with fixed weights

Résumé

Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) with fixed weights still possess the universal approximation property provided that approximated functions are univariate. But this phenomenon does not lay any restrictions on the number of neurons in the hidden layer. The more this number, the more the probability of the considered network to give precise results. In this note, we constructively prove that SLFNs with the fixed weight 1 and two neurons in the hidden layer can approximate any continuous function on a compact subset of the real line. The applicability of this result is demonstrated in various numerical examples. Finally, we show that SLFNs with fixed weights cannot approximate all continuous multivariate functions.
Fichier principal
Vignette du fichier
1708.06219.pdf (508.08 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01576061 , version 1 (22-08-2017)

Identifiants

Citer

Namig J Guliyev, Vugar E Ismailov. On the approximation by single hidden layer feedforward neural networks with fixed weights. Neural Networks, 2018, 98, pp.296-304. ⟨10.1016/j.neunet.2017.12.007⟩. ⟨hal-01576061⟩

Collections

TDS-MACS
258 Consultations
907 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More