A comparison of nonlinear optimization methods for supervised learning in multilayer feedforward neural networks

DOI10.1016/0377-2217(96)00035-5zbMath0912.90253MaRDI QIDQ1268172

Ming S. Hung, James W. Denton

Publication date: 18 October 1998

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0377-2217(96)00035-5

zbMATH Keywords

neural networks; pattern classification; supervised learning; training; multilayer feedforward networks

Mathematics Subject Classification ID

90C30: Nonlinear programming

68T05: Learning and adaptive systems in artificial intelligence

68T10: Pattern recognition, speech recognition

Related Items

TRANSFORM-ANN for online optimization of complex industrial processes: casting process as case study, Multilayer neural networks: an experimental evaluation of on-line training methods, A recursive algorithm for nonlinear least-squares problems

Uses Software

• L-BFGS

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Updating Quasi-Newton Matrices with Limited Storage
• Managerial Applications of Neural Networks: The Case of Bank Failure Predictions
• Factorized Variable Metric Methods for Unconstrained Optimization
• A GRG2-Based System for Training Neural Networks: Design and Computational Experience
• Function minimization by conjugate gradients
• Convergence Conditions for Ascent Methods
• A Family of Variable-Metric Methods Derived by Variational Means
• A new approach to variable metric algorithms
• On Steepest Descent
• The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations
• Conditioning of Quasi-Newton Methods for Function Minimization