Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

Inspired by detailed modelling of biological neurons, spiking neural networks (SNNs) are investigated as biologically plausible and high-performance models of neural computation. The sparse and binary communication between spiking neurons potentially enables powerful and energy-efficient neural netw...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Nature machine intelligence 2021-10, Vol.3 (10), p.905-913
Hauptverfasser:	Yin, Bojian, Corradi, Federico, Bohté, Sander M.
Format:	Artikel
Sprache:	eng
Schlagworte:	631/378/116/1925 639/705/1042 Accuracy Artificial neural networks Back propagation Back propagation networks Benchmarks Communication Deep learning Engineering Fashion models Gesture recognition Hardware Neural networks Neurons Performance enhancement Recurrent neural networks Speech recognition Spiking Time domain analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!