Publication detail

Stability of backpropagation learning rule

KRUPANSKÝ, P., PIVOŇKA, P.

Original Title

Stability of backpropagation learning rule

English Title

Stability of backpropagation learning rule

Type

conference paper

Language

en

Original Abstract

A control of real processes requires different approach to neural network learning. The presented modification of backpropagation learning algorithm changes a meaning of learning constants. A base of modification is stability condition of learning dynamics.

English abstract

A control of real processes requires different approach to neural network learning. The presented modification of backpropagation learning algorithm changes a meaning of learning constants. A base of modification is stability condition of learning dynamics.

Keywords

Neural networks, ARMA model, control, back-propagation, stability, the largest singular value, Euclidean norm

RIV year

2003

Released

15.09.2003

Publisher

Rektor der Hochschule Zittau/Gorlitz

Location

Zittau, Germany

ISBN

3-9808089-4-7

Book

Third EUSFLAT Proceedings

Edition

Neuveden

Edition number

1

Pages from

369

Pages to

374

Pages count

6

Documents

BibTex


@inproceedings{BUT8168,
  author="Petr {Krupanský} and Petr {Pivoňka}",
  title="Stability of backpropagation learning rule",
  annote="A control of real processes requires different
approach to neural network learning. The presented modification of backpropagation
learning algorithm changes a meaning of learning constants. A base of modification is stability condition of learning dynamics.",
  address="Rektor der Hochschule Zittau/Gorlitz",
  booktitle="Third EUSFLAT Proceedings",
  chapter="8168",
  edition="Neuveden",
  institution="Rektor der Hochschule Zittau/Gorlitz",
  year="2003",
  month="september",
  pages="369",
  publisher="Rektor der Hochschule Zittau/Gorlitz",
  type="conference paper"
}