Efficient connectivity and intrinsic noise separation in recurrent spiking neural networks trained with e-prop

Biologically plausible learning rules for neural networks, such as e-prop (eligibility propagation), are essential both for advancing neuromorphic computing and for understanding fundamental mechanisms of learning in animal brains. However, their behavior under different network conditions remains u...

Description complète

Détails bibliographiques

Auteurs principaux:	Davide Noè, Hideaki Yamamoto, Yuichi Katori, Shigeo Sato
Format:	Artigo
Langue:	Inglês
Publié:	IOP Publishing 2025-01-01
Collection:	Neuromorphic Computing and Engineering
Sujets:	recurrent neural networks spiking neurons eligibility propagation biologically plausible learning computational neuroscience
Accès en ligne:	https://doi.org/10.1088/2634-4386/ae0826
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!