Guest Editorial: Special Issue on New Advances in Deep-Transfer Learning

The papers in this special issue aim to present the most recent advances in deep transfer learning (DTL). While deep learning has achieved great success in big data applications, transfer learning (TL) is an important paradigm mainly for small/insufficient data applications, which utilizes the data/...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on emerging topics in computational intelligence Jg. 3; H. 5; S. 357 - 359
Hauptverfasser: Deng, Z., Lu, J., Wu, D., Choi, K.-S., Sun, S., Nojima, Y.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.10.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Big Data
Deep learning
Information filters
Machine learning
Special issues and sections
ISSN:2471-285X, 2471-285X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The papers in this special issue aim to present the most recent advances in deep transfer learning (DTL). While deep learning has achieved great success in big data applications, transfer learning (TL) is an important paradigm mainly for small/insufficient data applications, which utilizes the data/knowledge in one task to facilitate the learning in another relevant task. How to integrate DL and TL to combine their advantages is an interesting and important research topic. DTL is proposed to address this issue. Deep learning extracts knowledge from big data, which can then be used by TL for a new task/domain with small/insufficient data.
Bibliographie:SourceType-Scholarly Journals-1
content type line 14
ObjectType-Editorial-2
ObjectType-Commentary-1
ISSN:2471-285X
2471-285X
DOI:10.1109/TETCI.2019.2936641