Publication detail

Analysis of Recurrent Analog Neural Networks

TOBEŠ, Z. RAIDA, Z.

Original Title

Analysis of Recurrent Analog Neural Networks

English Title

Analysis of Recurrent Analog Neural Networks

Type

journal article - other

Language

en

Original 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.

English 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

RIV year

1998

Released

01.06.1998

Pages from

9

Pages to

14

Pages count

6

BibTex


@article{BUT39035,
  author="Zdeněk {Tobeš} and Zbyněk {Raida}",
  title="Analysis of Recurrent Analog Neural Networks",
  annote="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.",
  chapter="39035",
  howpublished="print",
  journal="Radioengineering",
  number="2",
  volume="7",
  year="1998",
  month="june",
  pages="9--14",
  type="journal article - other"
}