Backpropagating Through the Air: Deep Learning at Physical Layer Without Channel Models

Recent developments in applying deep learning techniques to train end-to-end communication systems have shown great promise in improving the overall performance of the system. However, most of the current methods for applying deep learning to train physical-layer characteristics assume the availabil...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE communications letters 2018-11, Vol.22 (11), p.2278-2281
Hauptverfasser:	Raj, Vishnu, Kalyani, Sheetal
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Channel models Communication systems Communications systems Computer simulation Deep learning Machine learning Neural networks optimization Perturbation methods Receivers Training Transmitters
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!