A comparison of Extended Kalman Filter and Levenberg-Marquardt methods for neural network training

Author

Deossa, Pablo ; Patiño, Julian ; Espinosa, Jairo ; Valencia, Felipe

Author_Institution

Fac. de Minas, Univ. Nac. de Colombia, Medellin, Colombia

fYear

2011

fDate

1-4 Oct. 2011

Firstpage

1

Lastpage

5

Abstract

This paper presents a performance comparison of both the Levenverg-Marquardt and Extended Kalman Filter methods for neural network training. As a testbed, an indoor localization problem was solved by the neural network from the RSSI data obtained through a experimental measurement. Both methods were used to train the network, and the MSE (mean squared error) was employed as the performance metric.

Keywords

Kalman filters; learning (artificial intelligence); mean square error methods; mobility management (mobile radio); neural nets; nonlinear filters; telecommunication computing; Levenberg-Marquardt method; RSSI data; experimental measurement; extended Kalman filter; indoor localization problem; mean squared error; neural network training; performance comparison; performance metric; Biological neural networks; Covariance matrix; Jacobian matrices; Kalman filters; Training; Vectors; Kalman ltering; Levenberg-Marquardt; RSSI; localization; neural networks; optimization;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics Symposium, 2011 IEEE IX Latin American and IEEE Colombian Conference on Automatic Control and Industry Applications (LARC)

Conference_Location

Bogota

Print_ISBN

978-1-4577-1689-8

Type

conf

DOI

10.1109/LARC.2011.6086835

Filename

6086835