S^3NN: time step reduction of spiking surrogate gradients for training energy efficient single-step spiking neural networks

DOI10.1016/J.NEUNET.2022.12.008MaRDI QIDQ6488751zbMATH OpenFDO

Authors Kazuma Suetake, Shin-ichi Ikegawa, Ryuji Saiin, Yoshihide Sawada

Publication date 18 October 2023

Published in Neural Networks (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

zbMATH Keywords

energy efficiencyspiking neural networkbinary neural networksingle-time stepsurrogate gradient

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Training much deeper spiking neural networks with a small number of time-steps
• Analyzing and accelerating the bottlenecks of training deep SNNs with backpropagation
• An FPGA implementation of deep spiking neural networks for low-power and fast classification

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• A Fast Learning Algorithm for Deep Belief Nets
• A logical calculus of the ideas immanent in nervous activity
• A novel spike distance
• An efficient learning procedure for deep Boltzmann machines
• Error-backpropagation in temporally encoded networks of spiking neurons
• SuperSpike: supervised learning in multilayer spiking neural networks

This page was built for publication: S\(^3\)NN: time step reduction of spiking surrogate gradients for training energy efficient single-step spiking neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6488751)