Comparing backpropagation with a genetic algorithm for neural network training

Comparing backpropagation with a genetic algorithm for neural network training

This article shows that the use of a genetic algorithm can provide better results for training a feedforward neural network than the traditional techniques of backpropagation. Using a chaotic time series as an illustration, we directly compare the genetic algorithm and backpropagation for effectiven...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Omega (Oxford) 1999-12, Vol.27 (6), p.679-684
Hauptverfasser: Gupta, Jatinder N.D, Sexton, Randall S
Format: Artikel
Sprache:eng
Schlagworte:
Algorithms
Applied sciences
Artificial intelligence
Back propagation
Backpropagation
Chaos theory
Comparative analysis
Computer science
control theory
systems
Connectionism. Neural networks
Empirical results
Exact sciences and technology
Genetic algorithm
Genetic algorithms
Neural networks
Neural networks Backpropagation Genetic algorithm Empirical results
Studies
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This article shows that the use of a genetic algorithm can provide better results for training a feedforward neural network than the traditional techniques of backpropagation. Using a chaotic time series as an illustration, we directly compare the genetic algorithm and backpropagation for effectiveness, ease-of-use, and efficiency for training neural networks.
ISSN:0305-0483
1873-5274
DOI:10.1016/S0305-0483(99)00027-4