Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral

While deep learning has been very beneficial in data-rich settings, tasks with smaller training set often resort to pre-training or multitask learning to leverage data from other tasks. In this case, careful consideration is needed to select tasks and model parameterizations such that updates from t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-08
Hauptverfasser:	Dery, Lucio M, Dauphin, Yann, Grangier, David
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Deep learning Image classification Machine learning Singular value decomposition Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!