Detail publikace

The Choice of Patterns in Training Set for Neural On-line Identification

Originální název

The Choice of Patterns in Training Set for Neural On-line Identification

Anglický název

The Choice of Patterns in Training Set for Neural On-line Identification

Jazyk

en

Originální abstrakt

The paper deals with on-line system identification for adaptive controller construction. The problem of an increasing number of data for neural network learning is solved by the choice of patterns in the training set based on the distance between patterns in the space of regressive model state vectors. Furthermore, the choice of scale to set this distance is considered. The objective is minimization of empirical approaches to allow for automation and wide application.

Anglický abstrakt

The paper deals with on-line system identification for adaptive controller construction. The problem of an increasing number of data for neural network learning is solved by the choice of patterns in the training set based on the distance between patterns in the space of regressive model state vectors. Furthermore, the choice of scale to set this distance is considered. The objective is minimization of empirical approaches to allow for automation and wide application.

BibTex


@inbook{BUT54954,
  author="Hynek {Vychodil} and Petr {Pivoňka} and Petr {Krupanský}",
  title="The Choice of Patterns in Training Set for Neural On-line Identification",
  annote="The paper deals with on-line system identification for adaptive controller construction. The problem of an increasing number of data for neural network learning is solved by the choice of patterns in the training set based on the distance between patterns in the space of regressive model state vectors. Furthermore, the choice of scale to set this distance is considered. The objective is minimization of empirical approaches to allow for automation and wide application.",
  address="Published by WSES Press, http://www.worldses.org",
  booktitle="Recent Advances in Circuits, Systems and Signal Processing",
  chapter="54954",
  edition="Electrical and Computer Engineering Series -
A series of Reference Books and Textbooks",
  institution="Published by WSES Press, http://www.worldses.org",
  year="2002",
  month="july",
  pages="250",
  publisher="Published by WSES Press, http://www.worldses.org",
  type="book chapter"
}