Memristor-Based Variation-Enabled Differentially Private Learning Systems for Edge Computing in IoT

Edge artificial intelligence (AI) achieves real-time local data analysis for IoT systems, enabling low-power and high-speed operation, but comes with privacy-preserving requirements. The memristor-based computing system is a promising solution for edge AI, but it needs a low-cost privacy protection...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE internet of things journal 2021-06, Vol.8 (12), p.9672-9682
Hauptverfasser:	Fu, Jingyan, Liao, Zhiheng, Liu, Jianqing, Smith, Scott C., Wang, Jinhui
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial intelligence Cycle-to-cycle variation Data analysis Data privacy differential privacy (DP) Edge computing Hardware Internet of Things learning systems Machine learning memristor Memristors neural network Noise noise injection Noise levels Privacy Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!