Continuously Constructive Deep Neural Networks

Traditionally, deep learning algorithms update the network weights, whereas the network architecture is chosen manually using a process of trial and error. In this paper, we propose two novel approaches that automatically update the network structure while also learning its weights. The novelty of o...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems Jg. 31; H. 4; S. 1124 - 1133
Hauptverfasser:	Irsoy, Ozan, Alpaydin, Ethem
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.04.2020 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Artificial neural networks Complexity theory Computer architecture Constructive learning Deep learning Learning algorithms Machine learning Network architecture Neural networks Parameterization Parameters Road transportation Task complexity Training
ISSN:	2162-237X, 2162-2388, 2162-2388
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!