<b>Parallel Back-Propagation <BR>for the Prediction of Time Series </b>

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
Frank.Thiesing@GAD.de
/prakt/prakt.html

Abstract:

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.

Introduction
Modified Back-Propagation
Parallelization
- On-Line Training
- Batch Learning
Implementation
Results
Conclusion and Future Work
References
About this document ...

Frank M. Thiesing
Mon Dec 19 16:19:41 MET 1994