Reducing the spike rate of deep spiking neural networks based on time-encoding

A primary objective of Spiking Neural Networks is a very energy-efficient computation. To achieve this target, a small spike rate is of course very beneficial given the event-driven nature of such a computation. A network that processes information encoded in spike timing can, by its nature, have su...

Full description

Bibliographic Details

Published in:	Neuromorphic Computing and Engineering
Main Authors:	Riccardo Fontanini, Alessandro Pilotto, David Esseni, Mirko Loghi
Format:	Article
Language:	English
Published:	IOP Publishing 2024-01-01
Subjects:	spiking neural networks spike rate learning strategy loss function
Online Access:	https://doi.org/10.1088/2634-4386/ad64fd