Abstract
A general purpose method for data modeling based on self-adapting Kohonen neural network has been presented. The method has been efficiently implemented on MIMD distributed memory machines. Future works concern the choice of different learning functions. A new, partially asynchronous, implementation is under development.
References
T.Kohonen, “Self-organization and associative memory”, Springer-Verlag, Berlin, 1988
J.Kangas, T.Kohonen, J.Laaksonen “Variants of self-organizing maps”, IEEE Trans. on Neural Net., Vol. 1, N. 1, March 1990
P.Flatt, A.Karp, “Measuring Parallel Processor Performance”, Comm. ACM (33), pp. 539–543, 1990
R.Devaney, “Caos and Fractals”, Addison-Welsey, 1990
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cremonesi, P. (1995). Kohonen neural networks: A parallel algorithm for automatic signal reconstruction. In: Hertzberger, B., Serazzi, G. (eds) High-Performance Computing and Networking. HPCN-Europe 1995. Lecture Notes in Computer Science, vol 919. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0046742
Download citation
DOI: https://doi.org/10.1007/BFb0046742
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59393-5
Online ISBN: 978-3-540-49242-9
eBook Packages: Springer Book Archive