Depth Selection for Deep ReLU Nets in Feature Extraction and Generalization

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantages of human ingenuity and prior knowledge. Thus it has triggered enormous research activities in machi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 4 vom: 12. Apr., Seite 1853-1868
1. Verfasser:	Han, Zhi (VerfasserIn)
Weitere Verfasser:	Yu, Siquan, Lin, Shao-Bo, Zhou, Ding-Xuan
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2022
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article Research Support, Non-U.S. Gov't