The Resistance to Label Noise in K-NN and DNN Depends on its Concentration

We investigate the classification performance of K-nearest neighbors (K-NN) and deep neural networks (DNNs) in the presence of label noise. We first show empirically that a DNN's prediction for a given test example depends on the labels of the training examples in its local neighborhood. This m...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-12
Hauptverfasser:	Drory, Amnon, Ratzon, Oria, Avidan, Shai, Giryes, Raja
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Classifiers Empirical analysis Neural networks Noise Noise prediction Noise sensitivity Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!