Publication detail

Automated modeling of microwave structures by enhanced neural networks

Petr ŠMÍD, Zbyněk RAIDA

Original Title

Automated modeling of microwave structures by enhanced neural networks

Type

journal article - other

Language

English

Original Abstract

The paper describes the methodology of the automated creation of neural models of microwave structures. During the creation process, artificial neural networks are trained using the combination of the particle swarm optimization and the quasi-Newton method to avoid critical training problems of the conventional neural nets. In the paper, neural networks are used to approximate the behavior of a planar microwave filter (moment method, Zeland IE3D). In order to evaluate the efficiency of neural modeling, global optimizations are performed using numerical models and neural ones. Both approaches are compared from the viewpoint of CPU-time demands and the accuracy. Considering conclusions, methodological recommendations for including neural networks to the microwave design are formulated

Keywords

Feed-forward neural network, recurrent neural net¬work, particle swarm optimization

Authors

Petr ŠMÍD, Zbyněk RAIDA

RIV year

2006

Released

1. 12. 2006

ISBN

1210-2512

Periodical

Radioengineering

Year of study

15

Number

4

State

Czech Republic

Pages from

71

Pages to

75

Pages count

5

BibTex

@article{BUT43724,
  author="Petr {Šmíd} and Zbyněk {Raida}",
  title="Automated modeling of microwave structures by enhanced neural networks",
  journal="Radioengineering",
  year="2006",
  volume="15",
  number="4",
  pages="5",
  issn="1210-2512"
}