Detail publikace

On-line Identification Based on Neural Networks using of Levenberg-Marquardt Method and Back-propagation Algorithm

Originální název

On-line Identification Based on Neural Networks using of Levenberg-Marquardt Method and Back-propagation Algorithm

Anglický název

On-line Identification Based on Neural Networks using of Levenberg-Marquardt Method and Back-propagation Algorithm

Jazyk

en

Originální abstrakt

In order to be able to control a system by means of an automatically adaptable controller, we have to adjust its parameters to the changes taking place in the system. For this purpose a number of methods have been developed. A frequently used identification method is the least-squares method, but we are limited by the choice of the suitable sampling period. The neural network seems to be a desirable solution because of its adaptation characteristics. Among the most used learning algorithms belong the Levenberg-Marquardt and back-propagation.

Anglický abstrakt

In order to be able to control a system by means of an automatically adaptable controller, we have to adjust its parameters to the changes taking place in the system. For this purpose a number of methods have been developed. A frequently used identification method is the least-squares method, but we are limited by the choice of the suitable sampling period. The neural network seems to be a desirable solution because of its adaptation characteristics. Among the most used learning algorithms belong the Levenberg-Marquardt and back-propagation.

BibTex


@article{BUT41839,
  author="Petr {Pivoňka} and Jiří {Dohnal}",
  title="On-line Identification Based on Neural Networks using of Levenberg-Marquardt Method and Back-propagation Algorithm",
  annote="In order to be able to control a system by means of an automatically adaptable controller, we have to adjust its parameters to the changes taking place in the system. For this purpose a number of methods have been developed.  A frequently used identification method is the least-squares method, but we are limited by the choice of the suitable sampling period. The neural network seems to be a desirable solution because of  its  adaptation characteristics.  Among the most used learning algorithms belong the Levenberg-Marquardt and back-propagation.",
  chapter="41839",
  number="2",
  volume="3",
  year="2004",
  month="march",
  pages="381--355",
  type="journal article - other"
}