An online gradient method with momentum for two-layer feedforward neural networks

DOI10.1016/j.amc.2009.02.038zbMath1187.68420OpenAlexW2030078509MaRDI QIDQ1026325

Naimin Zhang

Publication date: 24 June 2009

Published in: Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.amc.2009.02.038

zbMATH Keywords

convergenceneural networksmomentumonline gradient method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (5)

Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm ⋮ Convergence analysis for sigma-pi-sigma neural network based on some relaxed conditions ⋮ The Nesterov accelerated gradient algorithm for auto-regressive exogenous models with random lost measurements: interpolation method and auxiliary model method ⋮ Semistability of Steepest Descent with Momentum for Quadratic Functions ⋮ Training artificial neural networks by a hybrid PSO-CS algorithm

Cites Work

• Spectral projected subgradient with a momentum term for the Lagrangean dual approach
• Convergence of gradient method for Eelman networks
• Convergence of an online gradient method for feedforward neural networks with stochastic inputs.
• Training multilayer perceptrons via minimization of sum of ridge functions
• Deterministic convergence of an online gradient method for neural networks
• Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method
• Stability analysis of a three-term backpropagation algorithm
• Learning representations by back-propagating errors
• Projected Gradient Methods for Nonnegative Matrix Factorization

This page was built for publication: An online gradient method with momentum for two-layer feedforward neural networks