The convergence analysis of spikeprop algorithm with smoothing L₁/2 regularization

DOI10.1016/J.NEUNET.2018.03.007MaRDI QIDQ2179832zbMATH OpenOpenAlexWikidataFDO

Authors Junhong Zhao, Jacek M. Zurada, Jie Yang, Wei Wu

Publication date 13 May 2020

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2018.03.007

zbMATH Keywords

convergencesmoothing \(L_{1/2}\) regularizationsparsitySpikePropspiking neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Adaptive learning rate of SpikeProp based on weight convergence analysis
• On the Analytical Solution of Firing Time for SpikeProp
• Improved spikeprop for using particle swarm optimization
• Spiking neural networks: model, learning algorithms and applications
• Robust learning in SpikeProp

Cites work

• A modified gradient-based neuro-fuzzy learning algorithm and its convergence
• A Penalty-Function Approach for Pruning Feedforward Neural Networks
• Adaptive learning rate of SpikeProp based on weight convergence analysis
• Batch gradient method with smoothing \(L_{1/2}\) regularization for training of feedforward neural networks
• Convergence analysis of online gradient method for BP neural networks
• Convergence and monotonicity of an online gradient method with penalty for neural networks
• Error-backpropagation in temporally encoded networks of spiking neurons
• scientific article; zbMATH DE number 1916734 (Why is no real title available?)
• Improving neural network training solutions using regularisation
• Neural networks and physical systems with emergent collective computational abilities
• Spatial and temporal pattern analysis via spiking neurons

Cited in

(12)

• Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network
• Robust learning in SpikeProp
• Spiking neural network dynamic system modeling for computation of quantum annealing and its convergence analysis
• Analyzing and accelerating the bottlenecks of training deep SNNs with backpropagation
• Batch gradient method with smoothing \(L_{1/2}\) regularization for training of feedforward neural networks
• Training deep convolutional spiking neural networks with spike probabilistic global pooling
• On the Algorithmic Power of Spiking Neural Networks
• Robust echo state network with sparse online learning
• A novel parallel merge neural network with streams of spiking neural network and artificial neural network
• SMT-based modeling and verification of spiking neural networks: a case study
• Why Spiking Neural Networks Are Efficient: A Theorem
• Adaptive learning rate of SpikeProp based on weight convergence analysis

This page was built for publication: The convergence analysis of spikeprop algorithm with smoothing \(L_{1/2}\) regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2179832)