A Survey on Multi-Task Learning

Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on knowledge and data engineering Jg. 34; H. 12; S. 5586 - 5609
Hauptverfasser:	Zhang, Yu, Yang, Qiang
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 01.12.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms artificial intelligence Classification algorithms Clustering Cognitive tasks Computational modeling Data models Machine learning Modelling Multi-task learning Performance enhancement Supervised learning Task analysis Training Transfer learning
ISSN:	1041-4347, 1558-2191
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!