Probabilistic lower bounds for approximation by shallow perceptron networks

Limitations of approximation capabilities of shallow perceptron networks are investigated. Lower bounds on approximation errors are derived for binary-valued functions on finite domains. It is proven that unless the number of network units is sufficiently large (larger than any polynomial of the log...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 2017-07, Vol.91, p.34-41
Hauptverfasser:	Kůrková, Věra, Sanguineti, Marcello
Format:	Artikel
Sprache:	eng
Schlagworte:	Chernoff–Hoeffding bounds Lower bounds on approximation rates Model complexity Neural Networks (Computer) Perceptrons Shallow networks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!