Training a Sigmoidal Node Is Hard

This article proves that the task of computing near-optimal weights for sigmoidal nodes under the regression norm is NP-Hard. For the special case where the sigmoid is piecewise linear, we prove a slightly stronger result: that computing the optimal weights is NP-Hard. These results parallel that fo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural computation 1999-07, Vol.11 (5), p.1249-1260
1. Verfasser:	Hush, Don R
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithmics. Computability. Computer arithmetics Applied sciences Artificial intelligence Computer science control theory systems Connectionism. Neural networks Exact sciences and technology Learning and adaptive systems Theoretical computing
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!