Novel algorithms for noisy minimization problems with applications to neural networks training

DOI10.1007/S10957-006-9066-ZMaRDI QIDQ2370047zbMATH OpenOpenAlexFDO

Authors K. Sirlantzis, John D. Lamb, Wenbin Liu

Publication date 21 June 2007

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10957-006-9066-z

zbMATH Keywords

neural networks trainingnoisy optimizationNonlinear programmingstochastic programming

Mathematics Subject Classification ID

Neural nets and related approaches to inference from stochastic processes (62M45) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15)

Recommendations

• Novel supervisor-searcher cooperation algorithms for minimization problems with strong noise*
• Minimization algorithms based on supervisor and searcher cooperation
• Supervised training using global search methods.
• scientific article; zbMATH DE number 1552027
• scientific article; zbMATH DE number 1424367

Cites work

• scientific article; zbMATH DE number 4043678 (Why is no real title available?)
• scientific article; zbMATH DE number 48808 (Why is no real title available?)
• scientific article; zbMATH DE number 735099 (Why is no real title available?)
• scientific article; zbMATH DE number 928746 (Why is no real title available?)
• Learning representations by back-propagating errors
• Minimization algorithms based on supervisor and searcher cooperation
• On the Barzilai and Borwein choice of steplength for the gradient method
• Optimization algorithm with probabilistic estimation
• Oscillation and chaos in physiological control systems
• Testing Unconstrained Optimization Software
• The Barzilai and Borwein Gradient Method for the Large Scale Unconstrained Minimization Problem
• Two-Point Step Size Gradient Methods

Cited in

(6)

• An empirical study into finding optima in stochastic optimization of neural networks
• A gradient method for unconstrained optimization in noisy environment
• Descent direction method with line search for unconstrained optimization in noisy environment
• Novel supervisor-searcher cooperation algorithms for minimization problems with strong noise*
• Minimization algorithms based on supervisor and searcher cooperation
• Multilevel Objective-Function-Free Optimization with an Application to Neural Networks Training

Describes a project that uses

Uses Software

• UCI
• CMU Benchmarks
• minpack

This page was built for publication: Novel algorithms for noisy minimization problems with applications to neural networks training

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2370047)