Spiking Neural Networks Trained via Proxy

Spiking Neural Networks Trained via Proxy

We propose a new learning algorithm to train spiking neural networks (SNN) using conventional artificial neural networks (ANN) as proxy. We couple two SNN and ANN networks, respectively, made of integrate-and-fire (IF) and ReLU neurons with the same network architectures and shared synaptic weights....

Full description

Bibliographic Details
Main Authors: Saeed Reza Kheradpisheh, Maryam Mirsadeghi, Timothee Masquelier
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Spiking neural networks
supervised learning
proxy learning
rate coding
Online Access:https://ieeexplore.ieee.org/document/9810220/

Internet

https://ieeexplore.ieee.org/document/9810220/

Similar Items