Analyzing and accelerating the bottlenecks of training deep SNNs with backpropagation

DOI10.1162/NECO_A_01319MaRDI QIDQ3386449zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Ruizhi Chen, Ling Li

Publication date 4 January 2021

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_01319

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Training deep convolutional spiking neural networks with spike probabilistic global pooling
• An FPGA implementation of deep spiking neural networks for low-power and fast classification
• The convergence analysis of spikeprop algorithm with smoothing \(L_{1/2}\) regularization
• Spiking neural networks: model, learning algorithms and applications
• The maximum points-based supervised learning rule for spiking neural networks

Cites work

• Adaptive learning rate of SpikeProp based on weight convergence analysis
• Error-backpropagation in temporally encoded networks of spiking neurons
• scientific article; zbMATH DE number 6982943 (Why is no real title available?)
• Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics
• Robust spike-train learning in spike-event based weight update
• Spiking Neuron Models
• SuperSpike: supervised learning in multilayer spiking neural networks
• Supervised learning in multilayer spiking neural networks
• Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting

Cited in

(6)

• Skip-connected self-recurrent spiking neural networks with joint intrinsic parameter and synaptic weight training
• Training deep convolutional spiking neural networks with spike probabilistic global pooling
• An FPGA implementation of deep spiking neural networks for low-power and fast classification
• Second-order information bottleneck based spiking neural networks for sEMG recognition
• Training much deeper spiking neural networks with a small number of time-steps
• S^3NN: time step reduction of spiking surrogate gradients for training energy efficient single-step spiking neural networks

Describes a project that uses

Uses Software

• BinaryNet
• AlexNet
• ImageNet

This page was built for publication: Analyzing and accelerating the bottlenecks of training deep SNNs with backpropagation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3386449)