Training multilayer perceptrons via minimization of sum of ridge functions

DOI10.1023/A:1016249727555zbMath1002.90069OpenAlexW92865635MaRDI QIDQ1610214

Wei Wu, Xin Li, Guorui Feng

Publication date: 19 August 2002

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1016249727555

zbMATH Keywords

monotonicityweak convergenceneural networksridge functionsridge functionmultilayer perceptronsonline gradient algorithms

Mathematics Subject Classification ID

Nonlinear programming (90C30) Methods of quasi-Newton type (90C53) Neural networks for/in biological studies, artificial life and related topics (92B20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (7)

Characterization of an extremal sum of ridge functions ⋮ Convergence analysis for sigma-pi-sigma neural network based on some relaxed conditions ⋮ Approximation by sums of ridge functions with fixed directions ⋮ Convergence of an online gradient method for feedforward neural networks with stochastic inputs. ⋮ Convergence analysis of online gradient method for BP neural networks ⋮ Convergence analysis of batch gradient algorithm for three classes of sigma-pi neural networks ⋮ An online gradient method with momentum for two-layer feedforward neural networks

This page was built for publication: Training multilayer perceptrons via minimization of sum of ridge functions