A Parallel Recursive Prediction Error Algorithm for Training Layered Neural Networks
Chen, S., Cowan, C.F.N., Billings, S.A. et al. (1 more author)
(1989)
A Parallel Recursive Prediction Error Algorithm for Training Layered Neural Networks.
Research Report.
Acse Report 373
.
Dept of Automatic Control and System Engineering. University of Sheffield
Abstract
A new recursive prediction error algorithm is derived for the training of feedforward layered neural networks. The algorithm enables the weights in each neuron of the network to be updated in an efficient parallel manner and has better convergence properties than the classical back-propagation algorithm. The relationship between this new parallel algorithm and other existing learning algorithms is discussed. Examples taken from the fields of communication channel equalisation and non-linear systems modelling are used to demonstrate the superior performance of the new algorithm compared with the back propagation routine.
Metadata
Authors/Creators:
Chen, S.
Cowan, C.F.N.
Billings, S.A.
Grant, P.M.
Copyright, Publisher and Additional Information:
The Department of Automatic Control and Systems Engineering research reports offer a forum for the research output of the academic staff and research students of the Department at the University of Sheffield. Papers are reviewed for quality and presentation by a departmental editor. However, the contents and opinions expressed remain the responsibility of the authors. Some papers in the series may have been subsequently published elsewhere and you are advised to cite the later published version in these instances.
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)