Transfer Learning Algorithm With Knowledge Division Level

One of the major challenges of transfer learning algorithms is the domain drifting problem where the knowledge of source scene is inappropriate for the task of target scene. To solve this problem, a transfer learning algorithm with knowledge division level (KDTL) is proposed to subdivide knowledge o...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems Jg. 34; H. 11; S. 8602 - 8616
Hauptverfasser:	Han, Honggui, Liu, Hongxu, Yang, Cuili, Qiao, Junfei
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.11.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Domain drifting problem Elastic layers hierarchal transfer learning algorithm integrated learning method Knowledge Knowledge acquisition Knowledge engineering Knowledge management Learning systems Machine learning Measurement negative transfer Prediction algorithms Predictive models Task analysis Theoretical analysis Transfer learning
ISSN:	2162-237X, 2162-2388, 2162-2388
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!