Convergence analysis for sigma-pi-sigma neural network based on some relaxed conditions

DOI10.1016/J.INS.2021.11.044MaRDI QIDQ6149503zbMATH OpenOpenAlexFDO

Authors Qinwei Fan, Qian Kang, Jacek M. Zurada

Publication date 5 February 2024

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2021.11.044

zbMATH Keywords

convergenceboundednessbatch algorithmsigma-pi-sigma neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Analysis of algorithms (68W40) Methods of reduced gradient type (90C52)

Recommendations

• Convergence analysis of batch gradient algorithm for three classes of sigma-pi neural networks
• Convergence analysis of online gradient method for BP neural networks
• Boundedness and convergence analysis of a pi-sigma neural network based on online gradient method and sparse optimization
• Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network
• The convergence of stochastic gradient algorithms applied to learning in neural networks

Cites work

• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• An online gradient method with momentum for two-layer feedforward neural networks
• 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 of online gradient method with penalty for BP neural networks
• Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network
• Dynamic properties and a new learning mechanism in higher order neural networks
• Gradient Convergence in Gradient methods with Errors
• Multilayer feedforward networks are universal approximators
• Training multilayer perceptrons via minimization of sum of ridge functions

Cited in

(2)

• Convergence analysis of a novel high order networks model based on entropy error function
• Boundedness and convergence analysis of a pi-sigma neural network based on online gradient method and sparse optimization

This page was built for publication: Convergence analysis for sigma-pi-sigma neural network based on some relaxed conditions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6149503)