Kn. Lou et Ra. Perez, A NEW SYSTEM-IDENTIFICATION TECHNIQUE USING KALMAN FILTERING AND MULTILAYER NEURAL NETWORKS, Artificial intelligence in engineering, 10(1), 1996, pp. 1-8
The objective of this work is to use the back-propagation algorithm in
conjunction with Kalman filtering in order to establish a new self-le
arning technique of multilayer neural network (MNN). This new techniqu
e is developed by directly building a Kalman filtering model for each
perceptron in order to increase the adaptability of the MNN and to pro
vide for on-line nonlinear system identification. We demonstrate that
this new technique is faster and more stable than the classical back-p
ropagation algorithm for training multilayer perceptrons. We also find
that it is less sensitive to the initial weights and to the learning
parameters.