Title :
Comments on "Comparative analysis of backpropagation and the extended Kalman filter for training multilayer perceptrons"
Author :
Chandran, P. Sarat
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Inst., Singapore
Abstract :
In this note, the connection between the backpropagation algorithm and the extended Kalman filter is analyzed using an alternate form of representation for the Kalman gain term and shown to be much simpler than that reported by Ruck et al (1992).<>
Keywords :
Kalman filters; backpropagation; feedforward neural nets; Kalman gain; backpropagation; comparative analysis; extended Kalman filter; multilayer perceptrons; training; Algorithm design and analysis; Backpropagation algorithms; Covariance matrix; Equations; Feedforward neural networks; Kalman filters; Multi-layer neural network; Neural networks; Nonhomogeneous media; State estimation;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
