Summary
In recent years several neural networks learning algorithms have been developed by making use of the RLS recursion. These algorithms are based on the matrix inversion lemma and in some cases can be numerically ill-conditioned. For example the rounding errors can accumulate and cause errors to occur in both the estimated parameters and the covariance matrix. In this paper we present numerically robust learning algorithms based on the QR decomposition — a well known technique in the linear prediction theory.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
R. Azimi-Sadjadi, R.-J. Liou (1992) Fast learning process of multilayer neural networks using recursive least squares method, IEEE Transactions on Signal Processing, vol. 40, no. 2
J. Bilski (1996) The modified RLS algorithm for learning of the feedforward neural networks, II KSNiIZ, Szczyrk, pp. 32–38
J. Bilski (1996) New algorithms for learning of the feedforward neural networks, II KSNiIZ, Szczyrk, pp. 39–45
J. Bilski, K. Cpalka (1997) The extended RLS algorithm for neural network learning, III KSNiIZ, Kule, pp. 77–84
J. Bilski, L. Rutkowski (1998) A Fast Training Algorithm for Neural Networks, IEEE Transaction on Circuits and Systems — II, vol. 45,no. 6, June 1998: 749–753
P. Strobach (1990) Linear Prediction Theory - A Mathematical Basis for Adaptive Systems, Springer-Verlag, New York
P.E. Wellstead, M.B. Zarrop (1991) Self-tuning Systems — Control and Signal Processing, Wiley
T. Söderström, P. Stoica (1989) System Identification, Prentice Hall International
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bilski, J., Rutkowski, L. (2003). Numerically Robust Learning Algorithms for Feed Forward Neural Networks. In: Rutkowski, L., Kacprzyk, J. (eds) Neural Networks and Soft Computing. Advances in Soft Computing, vol 19. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1902-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1902-1_19
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-0005-0
Online ISBN: 978-3-7908-1902-1
eBook Packages: Springer Book Archive