Abstract: Parallel Back-Propagation for Sales Prediction on Transputer Systems

In this paper artificial neural networks are adapted to a short term forecast for the sale of articles in supermarkets. The data is modelled to fit into feedforward multilayer perceptron networks that are trained by the back-propagation algorithm. For enhancement this has been parallelized in different manners. One batch and two on-line training variants are implemented on parallel Transputer-based Parsytec systems: a GCel with T805 and a GC/PP with PowerPC processors and Transputer communication links. The parallelizations run with both the runtime environments Parix and PVM.

B.M. Cook, M.R. Jane, P. Nixon, P.M. Welch (eds):
Transputer Applications and Systems '95,
Proceedings of the 1995 World Transputer Congress, 4 - 6 Sep 1995, Harrogate, UK
IOS Press, 1995, pp. 318-331

HTML, HTML 3, Postscript (105 kB)