CURVATURE-DRIVEN SMOOTHING IN BACK PROPAGATION NEURAL NETWORKSFunded under: FP2-FUSION 10C
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 is proposed a modified error measure which can reduce the tendency to overfit 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.
Bibliographic Reference: REPORT: CLM-P880 EN (1990) 11PP. AVAILABLE FROM THE LIBRARIAN, UKAEA, CULHAM LABORATORY, ABINGDON, OXON. OX14 3DB (GB)
Record Number: 1989128096900 / Last updated on: 1992-11-04
Original language: EN
Available languages: en