Publication detail

Modeling EM Structures in the Neural Network Toolbox of MATLAB

RAIDA, Z.

Original Title

Modeling EM Structures in the Neural Network Toolbox of MATLAB

English Title

Modeling EM Structures in the Neural Network Toolbox of MATLAB

Type

journal article - other

Language

en

Original Abstract

Neural networks are electronic systems which can be trained to remember behavior of a modeled structure in given operational points, and which can be used to approximate behavior of the structure out of the training points. These approximation abilities of neural nets are demonstrated on modeling a frequency-selective surface, a microstrip transmission line and a microstrip dipole. Attention is turned to the accuracy and to the efficiency of neural models. The association of neural models and genetic algorithms, which can provide a global design tool, is discussed. Portions of matlab code illustrate descriptions.

English abstract

Neural networks are electronic systems which can be trained to remember behavior of a modeled structure in given operational points, and which can be used to approximate behavior of the structure out of the training points. These approximation abilities of neural nets are demonstrated on modeling a frequency-selective surface, a microstrip transmission line and a microstrip dipole. Attention is turned to the accuracy and to the efficiency of neural models. The association of neural models and genetic algorithms, which can provide a global design tool, is discussed. Portions of matlab code illustrate descriptions.

Keywords

Feed-forward neural networks, genetic algorithms, planar transmission lines, frequency selective surfaces, microstrip antennas, modeling, optimization methods

Released

01.01.2003

Pages from

46

Pages to

67

Pages count

22

BibTex


@article{BUT41102,
  author="Zbyněk {Raida}",
  title="Modeling EM Structures in the Neural Network Toolbox of MATLAB",
  annote="Neural networks are electronic systems which can be trained to remember behavior of a modeled structure in given operational points, and which can be used to approximate behavior of the structure out of the training points. These approximation abilities of neural nets are demonstrated on modeling a frequency-selective surface, a microstrip transmission line and a microstrip dipole. Attention is turned to the accuracy and to the efficiency of neural models. The association of neural models and genetic algorithms, which can provide a global design tool, is discussed. Portions of matlab code illustrate descriptions.",
  chapter="41102",
  number="6",
  volume="44",
  year="2003",
  month="january",
  pages="46",
  type="journal article - other"
}