Abstract
In previous papers e.g. [5] the effect on the learning properties of filtering or other preprocessing of input data to networks was considered. A strategy for adaptive filtering based directly on this analysis will be presented. We focus in Section 2 on linear networks and the delta rule since this simple case permits the approach to be easily tested. Numerical experiments on some simple problems show that the method does indeed enhance the performance of the epoch or off line method considerably. In Section 3, we discuss briefly the extension to non-linear networks and in particuar to backpropagation. The algorithm in its simple form is, however, less successful and current research focuses on a practicable extension to non-linear networks.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
The uci repository of machine learning and domain theories, ftp from ics.uci.edu:/pub/machine-learning-database.
C. Cachin, Pedagogical pattern selection strategies. Neural Networks Vol.7 No.1 (1994), pp175–181.
S.W. Ellacott, An analyis of the delta rule, in Proceedings of the International Neural Net Conference, Kluwer Academic Publishers (1990), pp956–959.
S.W. Ellacott, Techniques for the mathematical analysis of neural networks, J. Computational and Applied Mathematics, Vol.50 (1993), pp283–297.
S.W. Ellacott, Aspects of the numerical analysis of neural networks Acta Numerica, Cambridge University Press (1994).
E Isaacson and H.B. Keller, Analysis of numerical methods, Wiley (1966).
D.E. Rumelhart and J.L. McClelland. Parallel and distributed processing: explorations in the micro structure of cognition, Vols.l and 2, MIT (1986).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Ellacott, S.W., Easdown, A. (1997). Numerical Aspects of Machine Learning in Artificial Neural Networks. In: Ellacott, S.W., Mason, J.C., Anderson, I.J. (eds) Mathematics of Neural Networks. Operations Research/Computer Science Interfaces Series, vol 8. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-6099-9_28
Download citation
DOI: https://doi.org/10.1007/978-1-4615-6099-9_28
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7794-8
Online ISBN: 978-1-4615-6099-9
eBook Packages: Springer Book Archive