Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields

DOI10.1007/S00607-010-0123-YzbMath1238.78020OpenAlexW1969484815MaRDI QIDQ644857

M. Sammany, T. A. Harak, Elena Pelican

Publication date: 7 November 2011

Published in: Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00607-010-0123-y

zbMATH Keywords

genetic algorithmsill-posed problemsFredholm integral equation of the first kindregularized neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Fredholm integral equations (45B05) Numerical methods for inverse problems for integral equations (65R32) Electro- and magnetostatics (78A30) Neural and heuristic methods applied to problems in optics and electromagnetic theory (78M32)

Cites Work

• Unnamed Item
• Unnamed Item
• Inversion of Fredholm integral equations of the first kind with fully connected neural networks
• An initial value method for solving Fredholm integral equation of the first kind
• On solving Fredholm integral equations of the first kind using the interval programming algorithm of Robers
• A Technique for the Numerical Solution of Certain Integral Equations of the First Kind
• On fredholm integral equations of the first kind occurring in synthesis of electromagnetic fields
• Overtraining, regularization and searching for a minimum, with application to neural networks
• On the Numerical Solution of Fredholm Integral Equations of the First Kind by the Inversion of the Linear System Produced by Quadrature
• Learning representations by back-propagating errors
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields