Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction

Deep neural network (DNN) has been used as a learning model for modeling the hierarchical architecture of human brain. However, DNN suffers from problems of learning efficiency and computational complexity. To address these problems, deep sparse autoencoder network (DSAN) is used for learning facial...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Information sciences Jg. 428; S. 49 - 61
Hauptverfasser:	Chen, Luefeng, Zhou, Mengtian, Su, Wanjuan, Wu, Min, She, Jinhua, Hirota, Kaoru
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Inc 01.02.2018
Schlagworte:	Deep sparse autoencoder network Facial emotion recognition Human-robot interaction Softmax regression Softmax regression Human-robot interaction Facial emotion recognition Deep sparse autoencoder network
ISSN:	0020-0255, 1872-6291
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!