ADAPTIVE ALGORITHMS FOR NEURAL NETWORK SUPERVISED LEARNING: A DETERMINISTIC OPTIMIZATION APPROACH

DOI10.1142/S0218127406015805zbMath1156.92004OpenAlexW2099997745MaRDI QIDQ3598837

George D. Magoulas, Michael N. Vrahatis

Publication date: 3 February 2009

Published in: International Journal of Bifurcation and Chaos (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0218127406015805

zbMATH Keywords

unconstrained optimizationadaptive learningfeedforward neural networksJacobi processessupervised trainingbackpropagation training

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Nonlinear programming (90C30) Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (5)

An adaptive nonmonotone global Barzilai–Borwein gradient method for unconstrained optimization ⋮ Brain-Inspired Constructive Learning Algorithms with Evolutionally Additive Nonlinear Neurons ⋮ A novel artificial neural network-based interface coupling approach for partitioned fluid-structure interaction problems ⋮ Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing ⋮ On the nonmonotonicity degree of nonmonotone line searches

Uses Software

• BRENT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Parallel evolutionary training algorithms for ``hardware-friendly`` neural networks
• Cauchy's method of minimization
• Globally convergent modification of the quickprop method
• From linear to nonlinear iterative methods
• Adaptive stepsize algorithms for on-line training of neural networks.
• A new unconstrained optimization method for imprecise function and gradient values
• A class of gradient unconstrained minimization algorithms with adaptive stepsize
• Minimization of functions having Lipschitz continuous first partial derivatives
• Algorithm 666: Chabis: a mathematical software package for locating and evaluating roots of systems of nonlinear equations
• Solving systems of nonlinear equations using the nonzero value of the topological degree
• Quasi-Newton Methods, Motivation and Theory
• On Langevin Updating in Multilayer Perceptrons
• Geometry of learning: Visualizing the performance of neural network supervised training methods
• Ill-Conditioning in Neural Network Training Problems
• Iterative Solution Methods
• Iterative Solution of Nonlinear Equations in Several Variables
• Convergence Conditions for Ascent Methods
• Convergence Conditions for Ascent Methods. II: Some Corrections
• Rates of Convergence for a Class of Iterative Procedures
• AN APPLICATION OF THE METHOD OF STEEPEST DESCENTS TO THE SOLUTION OF SYSTEMS OF NON-LINEAR SIMULTANEOUS EQUATIONS
• Matrix Iterative Analysis

This page was built for publication: ADAPTIVE ALGORITHMS FOR NEURAL NETWORK SUPERVISED LEARNING: A DETERMINISTIC OPTIMIZATION APPROACH