Regularization tools for training large feed-forward neural networks using automatic differentiation∗

DOI10.1080/10556789808805701zbMath0913.68177OpenAlexW2069077343MaRDI QIDQ4227926

Per Lindström, Mårten Gulliksson, Jerry Eriksson, Per-Åke Wedin

Publication date: 25 May 1999

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/10556789808805701

zbMATH Keywords

feed-forward neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Parallel algorithms in computer science (68W10)

Related Items (4)

Local results for the Gauss-Newton method on constrained rank-deficient nonlinear least squares ⋮ Variable projections neural network training ⋮ Unnamed Item ⋮ KKT conditions for rank-deficient nonlinear least-square problems with rank-deficient nonlinear constraints

Uses Software

• Matlab
• Regularization tools
• ELSUNC_f90
• Neural Network Toolbox

Cites Work

• An implicit shift bidiagonalization algorithm for ill-posed systems
• A new linesearch algorithm for nonlinear least squares problems
• Inexact Newton Methods
• Global Convergence Properties of Conjugate Gradient Methods for Optimization
• Restart procedures for the conjugate gradient method
• Unnamed Item
• Unnamed Item

This page was built for publication: Regularization tools for training large feed-forward neural networks using automatic differentiation^∗