LEARNING ALGORITHMS OF LAYERED NEURAL NETWORKS VIA EXTENDED KALMAN FILTERS

 
see the original item page
in the repository's web site and access all digital files if the item*
share




1991 (EN)
LEARNING ALGORITHMS OF LAYERED NEURAL NETWORKS VIA EXTENDED KALMAN FILTERS (EN)

WATANABE, K (EN)
TZAFESTAS, SG (EN)
FUKUDA, T (EN)

N/A (EN)

Learning algorithms are described for layered feedforward type neural networks, in which a unit generates a real-valued output through a logistic function. The problem of adjusting the weights of internal hidden units can be regarded as a problem of estimating (or identifying) constant parametes with a non-linear observation equation. The present algorithm based on the extended Kalman filter has just the time-varying learning rate, while the well-known back-propagation (or generalized delta rule) algorithm based on gradient descent has a constant learning rate. From some simulation examples it is shown that when a sufficiently trained network is desired, the learning speed of the proposed algorithm is faster than that of the traditional back-propagation algorithm. (EN)

journalArticle

extended kalman filter (EN)
Neural Network (EN)
Learning Algorithm (EN)

Εθνικό Μετσόβιο Πολυτεχνείο (EL)
National Technical University of Athens (EN)

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE (EN)

1991


TAYLOR & FRANCIS LTD (EN)



*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)