Efficient Spiking Neural Networks With Radix Encoding

Spiking neural networks (SNNs) have advantages in latency and energy efficiency over traditional artificial neural networks (ANNs) due to their event-driven computation mechanism and the replacement of energy-consuming weight multiplication with addition. However, to achieve high accuracy, it usuall...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2024-03, Vol.35 (3), p.1-13
Hauptverfasser:	Wang, Zhehui, Gu, Xiaozhe, Goh, Rick Siow Mong, Zhou, Joey Tianyi, Luo, Tao
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Artificial neural networks Biological neural networks Coding Computational modeling Encoding Energy efficiency energy efficient Firing pattern Latency Mathematical models Multiplication Network latency Neural networks Neurons Open area test sites short spike train speedup spiking neural network (SNN) Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!