Abstract
The training of a neural network can be made using many different procedures; they allow to find the weights that minimize the discrepancies between targets and actual outputs of the network. The optimal weights can be found either in a direct way or using iterative techniques; in both cases it’s sometimes necessary (or simply useful) to evaluate the pseudo-inverse matrix of the projections of input examples into the function space created by the network. Every operation we have to perform to do this can however become dificult (and sometimes im- possible) when the dimension of this matrix is very large, so we deal with a way to subdivide it and to obtain our aim by a high parallel algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Broomhead, D. S., Lowe, D.: Multivariable functional interpolation and adaptive networks. Complex Systems 2 (1988) 321–355
Cancelliere, R.: Large database recognition tasks: a proposal. International Workshop on Neural Networks for Identification, Control, Robotics, and Signal/Image Processing, (1996)
Golub, G. H., Van Loan, C. F.: Matrix Computation 2nd edn. Baltimore, MD. John Hopkins University Press (1989)
Haykin S.: Adaptive Filter Theory. 2nd edn. Englewood Cliffs, NJ: Prentice-Hall (1991)
Haykin S.: Neural Networks, a Comprehensive Foundation. IEEE Computer Society Press (1994)
Poggio, T., Girosi, F.: Networks for approximation and learning. Proceedings of the IEEE 78, n.9, (1990) 1481–1497
Rumelhart: Learning internal representation by error propagation. Parallel Distribuited Processing (PDP): Exploration in the Microstructure of Cognition, MIT Press, Cambridge, Massachussetts Vol. 1, (1986) pp.318–362
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cancelliere, R. (2001). A High Parallel Procedure to Initialize the Output Weights of a Radial Basis Function or BP Neural Network. In: Sørevik, T., Manne, F., Gebremedhin, A.H., Moe, R. (eds) Applied Parallel Computing. New Paradigms for HPC in Industry and Academia. PARA 2000. Lecture Notes in Computer Science, vol 1947. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-70734-4_45
Download citation
DOI: https://doi.org/10.1007/3-540-70734-4_45
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41729-3
Online ISBN: 978-3-540-70734-9
eBook Packages: Springer Book Archive