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 QIDQ6488751FDOQ6488751

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

Publication date: 18 October 2023

Published in: Neural Networks (Search for Journal in Brave)

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

zbMATH Keywords

energy efficiencyspiking neural networkbinary neural networksingle-time stepsurrogate gradient

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Title not available (Why is that?)
• A novel spike distance
• A logical calculus of the ideas immanent in nervous activity
• Error-backpropagation in temporally encoded networks of spiking neurons
• A Fast Learning Algorithm for Deep Belief Nets
• An efficient learning procedure for deep Boltzmann machines
• 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)