Neural networks for predicting conditional probability densities: improved training scheme combining EM and RVFL

Husmeier, D. and Taylor, J.G. (1998) Neural networks for predicting conditional probability densities: improved training scheme combining EM and RVFL. Neural Networks, 11(1), pp. 89-116. (doi:10.1016/S0893-6080(97)00089-0)

Full text not currently available from Enlighten.

Abstract

Predicting conditional probability densities with neural networks requires complex (at least two-hidden-layer) architectures, which normally leads to rather long training times. By adopting the RVFL concept and constraining a subset of the parameters to randomly chosen initial values (such that the EM-algorithm can be applied), the training process can be accelerated by about two orders of magnitude. This allows training of a whole ensemble of networks at the same computational costs as would be required otherwise for training a single model. The simulations performed suggest that in this way a significant improvement of the generalization performance can be achieved.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Husmeier, Professor Dirk
Authors: Husmeier, D., and Taylor, J.G.
College/School:College of Science and Engineering > School of Mathematics and Statistics > Statistics
Journal Name:Neural Networks
ISSN:0893-6080

University Staff: Request a correction | Enlighten Editors: Update this record