Effects of direct input–output connections on multilayer perceptron neural networks for time series prediction

Feedforward neural network prediction is the most commonly used method in time series prediction. In view of the low prediction accuracy of the conventional BPNN model when the time series data contain a certain linear relationship, this paper describes a neural network approach for time series pred...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Soft computing (Berlin, Germany) Germany), 2020-04, Vol.24 (7), p.4729-4738
Hauptverfasser:	Wang, Yaoli, Wang, Lipo, Chang, Qing, Yang, Chunxia
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Algorithms Artificial neural networks Back propagation Back propagation networks Bias Brain Datasets Multilayer perceptrons Neural networks Propagation Stock prices Time series
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!