Abstract
This report presents several parallel implementations, on a MIMD machine, of a learning algorithm called OLS (Orthogonal Least Squares) for RBF (Radial Basis Function) neural networks. The sequential version is first described, and a straightforward parallel version is proposed. Two variants are developed, one of them reducing the complexity of the algorithm, and the other one improving the load balancing. An alternative is proposed for the storage of initial or intermediate data on local memory and discussed, according to the size of the application.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
D. S. Broomhead and D. Lowe. Multivariable Functional Interpolation and Adaptive Networks. Complex Systems, 2:321–355, 1988.
S. Chen, C. F. N. Cowan, and P. M. Grant. Orthogonal Least Squares Learning Alg. for Radial Basis Function Networks. IEEE Trans. on NN, 2(2):302–309, March 1991.
G. Cybenko. Approximation by Superposition of a Sigmoidal Function. Mathematics of Control, Signals, and Systems, 2(4):303–314, 1989.
V. Demian, F. Desprez, H. Paugam-Moisy, and M. Pourzandi. Parallel Implementation of RBF Neural Networks. Technical Report 96-11, LIP ENS Lyon, 1996.
R. Esser and R. Knecht. Intel Paragon XP/S — Architecture and Software Environment. Technical Report KFA-ZAM-IB-9305, Central Institute for Applied Mathematics, Research Center Julich (KFA), April 1993.
K. Hornik, M. Stinchcombe, and H. White. Universal Approximation of an Unknown Mapping and its Derivatives Using Multilayer Feedforward Networks. Neural Networks, 3(5):551–560, 1990.
Serge Miguet and Yves Robert. Elastic Load Balancing for Image Processing Plgorithms. In H. P. Zima, editor, Parallel Computation, Lect. Notes in Comp. Sci., pages 438–451, Salzburg, Austria, September 1991. 1st Int. ACPC Conf., Springer Verlag.
J. Moody and C. J. Darken. Fast Learning in Networks of Locally Tuned Processing Units. Neural Computation, 1(2):281–294, 1989.
J. Park and I. W. Sandberg. Universal Approximation Using Radial-Basis-Function Networks. Neural Computation, 3(2):246–257, 1991.
J. Park and I. W. Sandberg. Approximation and Radial Basis Function Networks. Neural Computation, 5(2):305–316, 1993.
S. Renais and R. Rohwer. Phoneme Classification Experiments Using Radial Basis Function. Proc. of Int. Joint Conf. on Neural Net., 1:461–467, 1989.
G. Verckovnik, C. R. Carter, and S. Haykin. Radial Basis Function Classification of Impulse Radar Waveforms. Proc. of Int. Joint Conf. on Neural Net., 1:45–50, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Demian, V., Desprez, F., Paugam-Moisy, H., Pourzandi, M. (1996). Parallel implementation of RBF neural networks. In: Bougé, L., Fraigniaud, P., Mignotte, A., Robert, Y. (eds) Euro-Par'96 Parallel Processing. Euro-Par 1996. Lecture Notes in Computer Science, vol 1124. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0024708
Download citation
DOI: https://doi.org/10.1007/BFb0024708
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61627-6
Online ISBN: 978-3-540-70636-6
eBook Packages: Springer Book Archive