Abstract
This paper deals with the parallel implementation of the back-propagation of errors learning algorithm. We propose two mapping schemes that allow to obtain two efficient parallel algorithms implemented on the Meiko CS-2 MIMD parallel computer. The parallel algorithms, obtained from the sequential code by means of simple and well localised modifications, are based on the use of a global operator whose straightforward hardware implementation could improve both performance and scalability of the proposed solutions.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Rumelhart, D.E., Hinton, G.E., and Williams, R.J.: Learning Representation by Back-Propagation of Errors. Nature, 323 (1986), 533–536.
Rumelhart, D.E., and McClelland, J.L.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge, MA, 1986.
Nordstrom, T., and Svensson, B.: Using and Designing Massively Parallel Computers for Artificial Neural Networks. Journal of Parallel and Distributed Computing, 14 (1992), 260–285.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Acierno, A.d., Palma, S. (1996). The back-propagation learning algorithm on the Meiko CS-2: Two mapping schemes. In: Liddell, H., Colbrook, A., Hertzberger, B., Sloot, P. (eds) High-Performance Computing and Networking. HPCN-Europe 1996. Lecture Notes in Computer Science, vol 1067. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61142-8_641
Download citation
DOI: https://doi.org/10.1007/3-540-61142-8_641
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61142-4
Online ISBN: 978-3-540-49955-8
eBook Packages: Springer Book Archive