Publication detail

High-Speed High-Accuracy Neural Networks for Automated Modeling of Electromagnetic Structures

P. Šmíd, Z. Raida, J. Láčík, Z. Lukeš

Original Title

High-Speed High-Accuracy Neural Networks for Automated Modeling of Electromagnetic Structures

English Title

High-Speed High-Accuracy Neural Networks for Automated Modeling of Electromagnetic Structures

Type

conference paper

Language

en

Original Abstract

Developing the original design method based on genetic models of designed electromagnetic structures is the motivation of this work. The paper deals with original genetic neural networks for modeling EM structures. A novel approach to learning artificial neural networks (ANN) by genetic algorithms (GA) and Levenberg–Marquardt (LM) method is described. Trai–ned ANN are used for the optimization of a H-shaped waveguide and a shielded microstrip transmission line.

English abstract

Developing the original design method based on genetic models of designed electromagnetic structures is the motivation of this work. The paper deals with original genetic neural networks for modeling EM structures. A novel approach to learning artificial neural networks (ANN) by genetic algorithms (GA) and Levenberg–Marquardt (LM) method is described. Trai–ned ANN are used for the optimization of a H-shaped waveguide and a shielded microstrip transmission line.

Keywords

waveguide, shielded transmission line, artificial neural network, genetic algorithm, Levenberg-Marquardt method, optimization

RIV year

2005

Released

12.09.2005

Publisher

Politecnico di Torino

Location

Torino, Italy

ISBN

88-8202-094-0

Book

Proceedings of joint 9-th International Conference on Electomagnetics in Advanced Applications ICEAA '05 and 11-th European Electromagnetic Structures Conference

Edition number

1

Pages from

213

Pages to

216

Pages count

4

BibTex


@inproceedings{BUT15382,
  author="Petr {Šmíd} and Zbyněk {Raida} and Jaroslav {Láčík} and Zbyněk {Lukeš}",
  title="High-Speed High-Accuracy Neural Networks for Automated Modeling of Electromagnetic Structures",
  annote="Developing the original design method based on genetic models of designed electromagnetic structures is the motivation of this work.
The paper deals with original genetic neural networks for modeling EM structures. A novel approach to learning artificial neural networks (ANN) by genetic algorithms (GA) and Levenberg–Marquardt (LM) method is described. Trai–ned ANN are used for the optimization of a H-shaped waveguide and a shielded microstrip transmission line.",
  address="Politecnico di Torino",
  booktitle="Proceedings of joint 9-th International Conference on Electomagnetics in Advanced Applications ICEAA '05 and 11-th European Electromagnetic Structures Conference",
  chapter="15382",
  institution="Politecnico di Torino",
  year="2005",
  month="september",
  pages="213",
  publisher="Politecnico di Torino",
  type="conference paper"
}