When Broad Learning System Meets Label Noise Learning: A Reweighting Learning Framework

Broad learning system (BLS) is a novel neural network with efficient learning and expansion capacity, but it is sensitive to noise. Accordingly, the existing robust broad models try to suppress noise by assigning each sample an appropriate scalar weight to tune down the contribution of noisy samples...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2023-10, Vol.PP, p.1-13
Hauptverfasser:	Liu, Licheng, Chen, Junhao, Yang, Bin, Feng, Qiying, Chen, C. L. Philip
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Adaptive systems Adaptive weight calculation broad learning system (BLS) Data models elementwise reweighting label noise learning Learning systems Noise measurement noisy data classification Time series analysis Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!