A method to resolve the overfitting problem in recurrent neural networks for prediction of complex systemsa behavior

A method to resolve the overfitting problem in recurrent neural networks for prediction of complex systemsa behavior

In this paper a new method to resolve the overfitting problem for predicting complex systemspsila behavior has been proposed. This problem occurs when a neural network loses its generalization. The method is based on the training of recurrent [abstract truncated by publisher].

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Brazilian Symposium on Neural Networks. Proceedings 2008-06, Vol.10, p.3723-3728
Hauptverfasser: Mahdaviani, K, Mazyar, H, Majidi, S, Saraee, M H
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper a new method to resolve the overfitting problem for predicting complex systemspsila behavior has been proposed. This problem occurs when a neural network loses its generalization. The method is based on the training of recurrent [abstract truncated by publisher].
ISSN:1522-4899
DOI:10.1109/IJCNN.2008.4634332