Result Details

Analysis of Recurrent Analog Neural Networks

TOBEŠ, Z.; RAIDA, Z. Analysis of Recurrent Analog Neural Networks. Radioengineering, 1998, vol. 7, no. 2, p. 9-14. ISSN: 1210-2512.

Type

journal article

Language

English

Authors

Tobeš Zdeněk, Ing.
Raida Zbyněk, prof. Dr. Ing.

Abstract

In this paper, an original rigorous analysis of recurrent analog neural networks, which are built from opamp neurons, is presented. The analysis, which comes from the approximate model of the operational amplifier, reveals causes of possible non-stable states and enables to determine convergence properties of the network. Results of the analysis are discussed in order to enable development of original robust and fast analog networks. In the analysis, the special attention is turned to the examination of the influence of real circuit elements and of the statistical parameters of processed signals to the parameters of the network.

Keywords

Analog recurrent neural networks, convergence properties, stability, modeling of operational amplifiers

Published

1998

Pages

9–14

Journal

Radioengineering, vol. 7, no. 2, ISSN 1210-2512

BibTeX

@article{BUT39035,
  author="Zdeněk {Tobeš} and Zbyněk {Raida}",
  title="Analysis of Recurrent Analog Neural Networks",
  journal="Radioengineering",
  year="1998",
  volume="7",
  number="2",
  pages="9--14",
  issn="1210-2512"
}

Departments

Faculty of Electrical Engineering and Communication (FEEC)