Parallel back-propagation for sales prediction on transputer systems

Autor(en): Thiesing, F.M.
Middelberg, U.
Vornberger, O. 
Stichwörter: Backpropagation; Forecasting; Interconnection networks; Management; Marketing; Parallel processing systems; Planning; Transputers, Batches; Feedforward multilayer perceptron networks, Neural networks
Erscheinungsdatum: 1995
Herausgeber: IOS Press, Amsterdam, Netherlands
Enthalten in: Concurrent Systems Engineering Series
Band: 46
Startseite: 318
Seitenende: 331
In his 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.
Conference of Proceedings of the 1995 3rd World Transputer Congress, WTC ; Conference Date: 4 September 1995 Through 6 September 1995; Conference Code:45265
ISSN: 13837575
Externe URL:

Show full item record

Page view(s)

Last Week
Last month
checked on Jun 13, 2024

Google ScholarTM