Performance evaluation of descent CG methods for neural network training

MaRDI QIDQ3084843zbMATH OpenFDO

Authors Ioannis E. Livieris, Panagiotis Pintelas

Publication date 25 March 2011

zbMATH Keywords

descent spectral conjugateneural networksnumerical experimentstraining algorithm

Mathematics Subject Classification ID

Iterative numerical methods for linear systems (65F10) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• A new conjugate gradient algorithm for training neural networks based on a modified secant equation
• scientific article; zbMATH DE number 19772
• scientific article; zbMATH DE number 1928800
• A new class of nonmonotone conjugate gradient training algorithms
• Fast Conjugate Gradient Algorithm for Feedforward Neural Networks

Cited in

(5)

• Fully complex conjugate gradient-based neural networks using Wirtinger calculus framework: deterministic convergence and its application
• Application of scaled nonlinear conjugate-gradient algorithms to the inverse natural convection problem
• Neural nets with a Newton conjugate gradient method on multiple GPUs
• A new class of nonmonotone conjugate gradient training algorithms
• A new conjugate gradient algorithm for training neural networks based on a modified secant equation

Describes a project that uses

Uses Software

• LIBOPT
• CG_DESCENT

This page was built for publication: Performance evaluation of descent CG methods for neural network training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3084843)