Frozen Overparameterization: A Double Descent Perspective on Transfer Learning of Deep Neural Networks

We study the generalization behavior of transfer learning of deep neural networks (DNNs). We adopt the overparameterization perspective -- featuring interpolation of the training data (i.e., approximately zero train error) and the double descent phenomenon -- to explain the delicate effect of the tr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-06
Hauptverfasser:	Dar, Yehuda, Luzi, Lorenzo, Baraniuk, Richard G
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Datasets Image classification Interpolation Machine learning Neural networks Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!