Unsupervised and efficient learning in sparsely activated convolutional spiking neural networks enabled by voltage-dependent synaptic plasticity

Unsupervised and efficient learning in sparsely activated convolutional spiking neural networks enabled by voltage-dependent synaptic plasticity

Spiking neural networks (SNNs) are gaining attention due to their energy-efficient computing ability, making them relevant for implementation on low-power neuromorphic hardware. Their biological plausibility has permitted them to benefit from unsupervised learning with bio-inspired plasticity rules,...

Full description

Bibliographic Details
Main Authors: Gaspard Goupy, Alexandre Juneau-Fecteau, Nikhil Garg, Ismael Balafrej, Fabien Alibart, Luc Frechette, Dominique Drouin, Yann Beilliard
Format: Article
Language:English
Published: IOP Publishing 2023-01-01
Series:Neuromorphic Computing and Engineering
Subjects:
convolutional spiking neural networks
sparsely activated neural networks
single spike neuron
unsupervised learning
voltage-dependent synaptic plasticity
hardware-friendly STDP
Online Access:https://doi.org/10.1088/2634-4386/acad98

Internet

https://doi.org/10.1088/2634-4386/acad98

Similar Items