Back propagation with expected source values

Back propagation with expected source values

The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural networks 1991, Vol.4 (5), p.615-618
1. Verfasser: Samad, Tariq
Format: Artikel
Sprache:eng
Schlagworte:
Applied sciences
Artificial intelligence
Back propagation
Computer science
control theory
systems
Connectionism. Neural networks
Exact sciences and technology
Neural networks
Supervised learning
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The back propagation learning rule converges significantly faster if expected values of source units are used for updating weights. The expected value of a unit can be approximated as the sum of the output of the unit and its error term. Results from numerous simulations demonstrate the comparative advantage of the new rule.
ISSN:0893-6080
1879-2782
DOI:10.1016/0893-6080(91)90015-W