Theory and Applications of Neural Networks pp 139-148
Curvature-Driven Smoothing in Backpropagation Neural Networks
- 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
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.
Unable to display preview. Download preview PDF.