Numerical methods of interval analysis in learning neural network

DOI10.1134/S0005117912110082MaRDI QIDQ2393053zbMATH OpenOpenAlexFDO

Authors P. V. Saraev

Publication date 7 August 2013

Published in Automation and Remote Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1134/s0005117912110082

zbMATH Keywords

numerical examplesalgorithmcomputer-aided experimentsinverse error propagationneural direct-propagation networksquadratic learning performance functional

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) General methods in interval analysis (65G40)

Recommendations

• A smoothing interval neural network
• scientific article; zbMATH DE number 96057
• An architecture of neural networks with interval weights and its application to fuzzy regression analysis
• scientific article; zbMATH DE number 671791
• scientific article; zbMATH DE number 1564026

Cites work

• scientific article; zbMATH DE number 2035082 (Why is no real title available?)
• scientific article; zbMATH DE number 1767706 (Why is no real title available?)
• Global robust stability of a class of discrete-time interval neural networks
• Interval standard neural network models for nonlinear systems

Cited in

(6)

• scientific article; zbMATH DE number 96057 (Why is no real title available?)
• Bounding the search space for global optimization of neural networks learning error: an interval analysis approach
• Advances in Neural Networks – ISNN 2005
• scientific article; zbMATH DE number 1564026 (Why is no real title available?)
• Solving the linear interval tolerance problem for weight initialization of neural networks
• Identification of a complex control object with frequency characteristics obtained experimentally with its dynamic neural network model

This page was built for publication: Numerical methods of interval analysis in learning neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2393053)