Detail výsledku

Improvements of Analog Neural Networks Based on Kalman Filter

TOBEŠ, Z., RAIDA, Z. Improvements of Analog Neural Networks Based on Kalman Filter. Radioengineering, 2002, vol. 11, no. 3, 8 p. ISSN: 1210-2512.
Typ
článek v časopise
Jazyk
anglicky
Autoři
Tobeš Zdeněk, Ing.
Raida Zbyněk, prof. Dr. Ing.
Abstrakt

In the paper, original improvements of recurrent analog neural networks, which are based on Kalman filter, are presented. These improvements eliminate some disadvantages of the classical Kalman neural network and enable a real time processing of quickly changing signals, which appear in adaptive antennas and similar applications. This goal is reached using such circuit elements, which increase the convergence rate of the network and decrease the dependence of convergence rate on the ratio of eigenvalues of the correlation matrix of input signals.

Klíčová slova

Kalman filter, analog recurrent neural networks, convergence rate, stability

Rok
2002
Strany
8
Časopis
Radioengineering, roč. 11, č. 3, ISSN 1210-2512
BibTeX 
@article{BUT40903,
  author="Zdeněk {Tobeš} and Zbyněk {Raida}",
  title="Improvements of Analog Neural Networks Based on Kalman Filter",
  journal="Radioengineering",
  year="2002",
  volume="11",
  number="3",
  pages="8",
  issn="1210-2512"
}
Pracoviště
Ústav radioelektroniky (UREL)
Nahoru