Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields (Q644857)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields |
scientific article; zbMATH DE number 5968766
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields |
scientific article; zbMATH DE number 5968766 |
Statements
Hybrid neuro-genetic based method for solving ill-posed inverse problem occurring in synthesis of electromagnetic fields (English)
0 references
7 November 2011
0 references
The authors propose a two-step method for the approximate solution of a first kind Fredholm integral equation with smooth kernel on a finite interval. The first step is to find an initial solution by using a genetic algorithm, and the second is to refine the solution employing a regularized neural network. Numerical results are presented for an integral equation occurring in the synthesis of electrostatic fields.
0 references
Fredholm integral equation of the first kind
0 references
ill-posed problems
0 references
genetic algorithms
0 references
regularized neural networks
0 references
0 references
0 references
0 references
