Detail výsledku

Genetic Neural Networks for Modeling Dipole Antennas

ŠMÍD, P., RAIDA, Z., LUKEŠ, Z. Genetic Neural Networks for Modeling Dipole Antennas. WSEAS Transactions on Computers, 2004, vol. 6, no. 3, 5 p. ISSN: 1109-2750.
Typ
článek v časopise
Jazyk
angličtina
Autoři
Šmíd Petr, Ing., Ph.D., UREL (FEKT)
Raida Zbyněk, prof. Dr. Ing., UREL (FEKT)
Lukeš Zbyněk, Ing., Ph.D., UREL (FEKT)
Abstrakt

The paper deals with original genetic neural networks for modeling wire dipole antennas. A novel approach to learning artificial neural networks (ANN) by genetic algorithms (GA) is described. The goal is to compare the learning abilities of neural antenna models trained by the GA and models trained by gradient algorithms. Developing the original design method based on genetic models of designed electromagnetic structures is the motivation of this work. Two types of ANN, the recurrent Elman ANN and the feed-forward one, are implemented in MATLAB. Results of training abilities are discussed.

Klíčová slova

artificial neural networks, genetic algorithm, wire dipole antenna

Rok
2004
Strany
5
Časopis
WSEAS Transactions on Computers, roč. 6, č. 3, ISSN 1109-2750
Kniha
WSEAS Transactions on Computers, Issue 6, Volume 3, December 2004
Konference
4th WSEAS International Conference on Applied Informatics and Communications
Místo
Puerto De La Cruz, Tenerife
BibTeX 
@article{BUT45635,
  author="Petr {Šmíd} and Zbyněk {Raida} and Zbyněk {Lukeš}",
  title="Genetic Neural Networks for Modeling Dipole Antennas",
  journal="WSEAS Transactions on Computers",
  year="2004",
  volume="6",
  number="3",
  pages="5",
  issn="1109-2750"
}
Pracoviště
Ústav radioelektroniky (UREL)
Nahoru