Bounding the search space for global optimization of neural networks learning error: an interval analysis approach

zbMATH Open1392.68335MaRDI QIDQ2834501FDOQ2834501

Authors Stavros P. Adam, George D. Magoulas, Dimitrios A. Karras, Michael N. Vrahatis 

Publication date 22 November 2016

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL http://jmlr.csail.mit.edu/papers/v17/14-350.html

zbMATH Keywords

interval analysisneural network traininginterval linear equationsalgebraic solutionbound constrained global optimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonconvex programming, global optimization (90C26) Derivative-free methods and methods using generalized derivatives (90C56)

Recommendations

• A global optimization approach to neural network training
• scientific article; zbMATH DE number 1961132
• Numerical methods of interval analysis in learning neural network
• Supervised training using global search methods.
• Artificial Intelligence and Soft Computing - ICAISC 2004

Cited In (2)

• Global optimization issues in deep network regression: an overview
• Globally optimal bounding ellipsoid algorithm for parameter estimation using artificial neural networks

Uses Software

• Matlab
• INTLAB
• mctoolbox

This page was built for publication: Bounding the search space for global optimization of neural networks learning error: an interval analysis approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2834501)