Nano-oscillator-based classification with a machine learning-compatible architecture

Pattern classification architectures leveraging the physics of coupled nano-oscillators have been demonstrated as promising alternative computing approaches but lack effective learning algorithms. In this work, we propose a nano-oscillator based classification architecture where the natural frequenc...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of applied physics 2018-10, Vol.124 (15)
Hauptverfasser:	Vodenicarevic, Damir, Locatelli, Nicolas, Grollier, Julie, Querlioz, Damien
Format:	Artikel
Sprache:	eng
Schlagworte:	Applied physics Architecture Artificial intelligence Back propagation Classification Distance learning Machine learning Neural networks Oscillators Pattern classification Physics Resonant frequencies
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!