Adaptive Random Forests for Energy-Efficient Inference on Microcontrollers

Random Forests (RFs) are widely used Machine Learning models in low-power embedded devices, due to their hardware friendly operation and high accuracy on practically relevant tasks. The accuracy of a RF often increases with the number of internal weak learners (decision trees), but at the cost of a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-05
Hauptverfasser:	Daghero, Francesco, Burrello, Alessio, Xie, Chen, Benini, Luca, Calimera, Andrea, Macii, Enrico, Poncino, Massimo, Pagliari, Daniele Jahier
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Classification Computer Science - Learning Decision trees Electronic devices Embedded systems Energy consumption Energy costs Inference Machine learning Microcontrollers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!