Training multi-layered neural network with a trust-region based algorithm

DOI10.1051/M2AN/1990240405231zbMATH Open0707.90097OpenAlexW2583686046MaRDI QIDQ3489808FDOQ3489808

Authors:

Publication date: 1990

Published in: ESAIM: Mathematical Modelling and Numerical Analysis (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/193605

Recommendations

• Trust region method in neural network
• scientific article; zbMATH DE number 1054676
• Neural network training and simulation using a multidimensional optimization system
• scientific article; zbMATH DE number 1727374
• scientific article; zbMATH DE number 1424367

zbMATH Keywords

trust-region techniquetraining a neural network

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Nonconvex programming, global optimization (90C26) Computational methods for problems pertaining to operations research and mathematical programming (90-08) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Computing a Trust Region Step
• Title not available (Why is that?)
• Title not available (Why is that?)
• Convex Analysis
• Title not available (Why is that?)
• Smoothing by spline functions.
• Smoothing by spline functions. II
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Testing a Class of Methods for Solving Minimization Problems with Simple Bounds on the Variables
• Title not available (Why is that?)
• On the superlinear convergence of a trust region algorithm for nonsmooth optimization
• Computing Optimal Locally Constrained Steps
• Title not available (Why is that?)
• Newton’s Method with a Model Trust Region Modification
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Approximate solution of the trust region problem by minimization over two-dimensional subspaces
• A Family of Trust-Region-Based Algorithms for Unconstrained Minimization with Strong Global Convergence Properties
• Title not available (Why is that?)
• Title not available (Why is that?)
• On the use of directions of negative curvature in a modified newton method
• A second-order method for unconstrained optimization
• Quasi-Newton Methods for Unconstrained Optimization
• An Example of Only Linear Convergence of Trust Region Algorithms for Non-smooth Optimization
• The Use of Linear Programming for the Solution of Sparse Sets of Nonlinear Equations
• A Modified Newton’s Method for Unconstrained Minimization

Cited In (4)

• Multilevel Artificial Neural Network Training for Spatially Correlated Learning
• Stability of lagrangian duality for nonconvex quadratic programming. Solution methods and applications in computer vision
• Comparative studies on mesh-free deep neural network approach versus finite element method for solving coupled nonlinear hyperbolic/wave equations
• Difference of convex functions optimization algorithms (DCA) for globally minimizing nonconvex quadratic forms on Euclidean balls and spheres

Uses Software

• GQTPAR

This page was built for publication: Training multi-layered neural network with a trust-region based algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3489808)