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

DOI10.1016/J.INS.2021.11.044OpenAlexW3217439888MaRDI QIDQ6149503

Qian Kang, Jacek M. Zurada, Qinwei Fan

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

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

Cites Work

• Unnamed Item
• Unnamed Item
• 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
• An online gradient method with momentum for two-layer feedforward neural networks
• Training multilayer perceptrons via minimization of sum of ridge functions
• Multilayer feedforward networks are universal approximators
• Dynamic properties and a new learning mechanism in higher order neural networks
• Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network
• Gradient Convergence in Gradient methods with Errors

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