Approximation capability of two hidden layer feedforward neural networks with fixed weights

We algorithmically construct a two hidden layer feedforward neural network (TLFN) model with the weights fixed as the unit coordinate vectors of the d-dimensional Euclidean space and having 3d+2 number of hidden neurons in total, which can approximate any continuous d-variable function with an arbit...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neurocomputing (Amsterdam) 2018-11, Vol.316, p.262-269
Hauptverfasser:	Guliyev, Namig J., Ismailov, Vugar E.
Format:	Artikel
Sprache:	eng
Schlagworte:	Activation function Computer Science Hidden layer Information Theory Mathematics Multilayer feedforward neural network Neural and Evolutionary Computing Numerical Analysis Sigmoidal function The Kolmogorov superposition theorem Weight
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!