for the Prediction of Time Series
Parallel Back-Propagation for the Prediction of Time Series
Frank M. Thiesing, Ulrich Middelberg, Oliver Vornberger
University of Osnabrück
Dept. of Math. / Computer Science
D-49069 Osnabrück, Germany
Artificial neural networks are suitable for the prediction of chaotic time series.
A modified back-propagation algorithm with neuron splitting is used to train
feed-forward multilayer perceptron networks for prediction.
There are two ways of parallelizing:
distributing the training set for batch learning or distribute
the vector-matrix-operations for on-line training.
Three implementation are compaired: PVM on a workstation cluster and PARIX
and the new PVM/PARIX on a Transputer system.
Results about the quality of forecasting an examplary time series
and speedups of the parallel programs are presented.
Frank M. Thiesing
Mon Dec 19 16:19:41 MET 1994