Enhancing temporal learning in recurrent spiking networks for neuromorphic applications

Training Recurrent Spiking Neural Networks (RSNNs) with binary spikes for tasks of extended time scales presents a challenge due to the amplified vanishing gradient problem during back propagation through time. This paper introduces three crucial elements that significantly enhance the memory and ca...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Ismael Balafrej, Soufiyan Bahadi, Jean Rouat, Fabien Alibart
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	IOP Publishing 2025-01-01
סדרה:	Neuromorphic Computing and Engineering
נושאים:	spiking neural network synaptic delays surrogate gradient descent neural dynamics
גישה מקוונת:	https://doi.org/10.1088/2634-4386/add293
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!