On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression

In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for the deep neural network (DNN) based vector-to-vector regression. The goal of this work is two-fold: (i) presenting performance bounds of MAE, and (ii) demonstrating new properties of MAE that make it more ap...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE signal processing letters 2020-01, Vol.27, p.1-1
Hauptverfasser:	Qi, Jun, Du, Jun, Siniscalchi, Sabato Marco, Ma, Xiaoli, Lee, Chin-Hui
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks deep neural network Errors Mean absolute error mean squared error Neural networks Regression speech enhancement Speech processing Upper bounds vector-to-vector regression
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!