A new class of nonmonotone conjugate gradient training algorithms

DOI10.1016/J.AMC.2015.05.053zbMATH Open1410.65235OpenAlexW628352727MaRDI QIDQ669374FDOQ669374

Authors Ioannis E. Livieris, Panagiotis Pintelas 

Publication date 15 March 2019

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

Full work available at URL https://doi.org/10.1016/j.amc.2015.05.053

zbMATH Keywords

artificial neural networksglobal convergenceconjugate gradient algorithmnonmonotone line search

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) 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
• A new class of conjugate gradient methods with extended nonmonotone line search
• Performance evaluation of descent CG methods for neural network training
• A nonmonotone conjugate gradient algorithm for unconstrained optimization
• A new family of conjugate gradient methods

Cites Work

• scientific article; zbMATH DE number 3843083 (Why is no real title available?)
• scientific article; zbMATH DE number 88930 (Why is no real title available?)
• scientific article; zbMATH DE number 3278849 (Why is no real title available?)
• A Nonmonotone Line Search Technique for Newton’s Method
• A comparative study of neural network based feature extraction paradigms
• A descent modified Polak–Ribière–Polyak conjugate gradient method and its global convergence
• A dynamic all parameters adaptive BP neural networks model and its application on oil reservoir prediction
• A new conjugate gradient algorithm for training neural networks based on a modified secant equation
• A survey of nonlinear conjugate gradient methods
• Avoiding the Maratos Effect by Means of a Nonmonotone Line Search I. General Constrained Problems
• Benchmarking optimization software with performance profiles.
• Convergence of descent method without line search
• Exponential stability of continuous-time and discrete-time cellular neural networks with delays
• Forecasting electrical consumption by integration of neural network, time series and ANOVA
• Function minimization by conjugate gradients
• Global convergence of a modified Fletcher-Reeves conjugate gradient method with Armijo-type line search
• Global convergence of nonmonotone descent methods for unconstrained optimization problems
• Globally convergent modified Perry's conjugate gradient method
• Integration of artificial neural networks and genetic algorithm to predict electrical energy consumption
• Methods of conjugate gradients for solving linear systems
• Modified nonmonotone Armijo line search for descent method
• Numerical Optimization
• On the nonmonotone line search
• Performance evaluation of descent CG methods for neural network training
• Sufficient descent nonlinear conjugate gradient methods with conjugacy condition
• The convergence of conjugate gradient method with nonmonotone line search
• Two descent hybrid conjugate gradient methods for optimization
• Two modified Dai-Yuan nonlinear conjugate gradient methods

Cited In (4)

• Performance evaluation of descent CG methods for neural network training
• Accelerating optimization by tracing valley
• A new conjugate gradient algorithm for training neural networks based on a modified secant equation
• An auto-adjustable semi-supervised self-training algorithm

Uses Software

• UCI

This page was built for publication: A new class of nonmonotone conjugate gradient training algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q669374)