Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data

Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially prominent when multilayer deep learning architectures are used. T...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2018-12
Hauptverfasser:	Ayinde, Babajide O, Zurada, Jacek M
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Deep learning Feature extraction Human performance Multilayers Regularization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!