Curvature-Driven Smoothing in Backpropagation Neural Networks

  • C M Bishop
Conference paper

DOI: 10.1007/978-1-4471-1833-6_8

Part of the Perspectives in Neural Computing book series (PERSPECT.NEURAL)
Cite this paper as:
Bishop C.M. (1992) Curvature-Driven Smoothing in Backpropagation Neural Networks. In: Taylor J.G., Mannion C.L.T. (eds) Theory and Applications of Neural Networks. Perspectives in Neural Computing. Springer, London

Abstract

The standard backpropagation learning algorithm for feedforward networks aims to minimise the mean square error defined over a set of training data. This form of error measure can lead to the problem of over-fitting in which the network stores individual data points from the training set, but fails to generalise satisfactorily for new data points. In this paper we propose a modified error measure which can reduce the tendency to over-fit and whose properties can be controlled by a single scalar parameter. The new error measure depends both on the function generated by the network and on its derivatives. A new learning algorithm is derived which can be used to minimise such error measures.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag London Limited 1992

Authors and Affiliations

  • C M Bishop

There are no affiliations available

Personalised recommendations