A neural network trained with the extended Kalman algorithm used for the equalization of a binary communication channel

Author

Birgmeier, Martin

Author_Institution

Inst. fur Nachrichtentech. und Hochfrequenztech., Tech. Univ. Wien, Austria

fYear

1994

fDate

6-8 Sep 1994

Firstpage

527

Lastpage

534

Abstract

This paper describes a feedforward neural network architecture trained with the extended Kalman filter algorithm instead of the standard (LMS) method. It presents a simplified recursive procedure for calculating the necessary derivatives. The resulting algorithm is then used to train a network to adapt to the decision boundary of an optimal receiver for a binary communication channel, resulting in increased convergence speed and better approximation properties

Keywords

Kalman filters; convergence; feedforward neural nets; learning (artificial intelligence); telecommunication channels; approximation properties; binary communication channel; convergence speed; decision boundary; equalization; extended Kalman filter algorithm; feedforward neural network architecture; optimal receiver; recursive procedure; Artificial neural networks; Backpropagation algorithms; Communication channels; Convergence; Equations; Feedforward neural networks; Kalman filters; Least squares approximation; Neural networks; Partitioning algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop

Conference_Location

Ermioni

Print_ISBN

0-7803-2026-3

Type

conf

DOI

10.1109/NNSP.1994.366013

Filename

366013