Template-based procedures for neural network interpretation

Although neural networks often achieve impressive learning and generalization performance, their internal workings are typically all but impossible to decipher. This characteristic of the networks, their opacity, is one of the disadvantages of connectionism compared to more traditional, rule-oriente...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 1999-04, Vol.12 (3), p.479-498
Hauptverfasser:	Alexander, J.A., Mozer, M.C.
Format:	Artikel
Sprache:	eng
Schlagworte:	Applied sciences Artificial intelligence Boolean Computer science control theory systems Connectionism. Neural networks Connectionist networks Exact sciences and technology Neural networks Rule extraction Sigmoidal units
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!