Regularized Differentiable Architecture Search

Differentiable architecture search (DARTS) transforms architectural optimization into a super-network optimization by stacking two cells (2 c.). However, repeatedly stacking two cells is a sub-optimal operation since cells in different depths should be various. Besides, we find that the performance...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE embedded systems letters 2023-09, Vol.15 (3), p.1-1
Hauptverfasser:	Wang, Lanfei, Xie, Lingxi, Zhao, Kaili, Guo, Jun, Tian, Qi
Format:	Artikel
Sprache:	eng
Schlagworte:	Automated Machine Learning Computer architecture Computer vision Deep learning Embedded systems Machine learning Mathematical analysis Neural Architecture Search Neural networks Optimization Resource allocation Resource management Stacking Topology Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!