Detail publikace

Analysis of Recurrent Analog Neural Networks

TOBEŠ, Z. RAIDA, Z.

Originální název

Analysis of Recurrent Analog Neural Networks

Typ

článek v časopise - ostatní, Jost

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

TOBEŠ, Z.; RAIDA, Z.

Rok RIV

1998

Vydáno

1. 6. 1998

ISSN

1210-2512

Periodikum

Radioengineering

Ročník

7

Číslo

2

Stát

Česká republika

Strany od

9

Strany do

14

Strany počet

6

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"
}