Abstract
An original hardware architecture implementing the self-organizing feature maps, which is one of the most powerful and efficent neural network algorithm, is presented. The architecture, contrary to the most investigated hardware implementations of neural networks, is a full digital one and it may be easily built by using the standard VLSI techniques.
Simulations of the architecture at a functional/logic level are carried on, showing the interesting capabilties of the architecture. An extensive application to the task of recognition of very noisy patterns is also described.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Kohonen, T., Self-Organization and Associative Memory. Springer-Verlag, Berlin, 1989.
Aleksander, I., Stonham, T.J., A Guide to Pattern Recognition Using Random Access Memories, IEE J. Comput. & Digital Tech. 2 (1), 29–40, 1979.
Aleksander, I., (ed.) Neural Computing Architectures. North Oxford Academic, London, 1989.
Steck, G.P., Stochastic model for the Browning-Bledsoe pattern Recognition Scheme, IRE Trans. Electronic Computers, EC-11, 274–282, 1962.
Chella, A., Gioiello, M., Sorbello, F., A New Digital Architecture Implementing the Kohonen Maps, in: Cappellini, V., Constantinides, A.G. (eds.), Digital Signal Processing '91 — Proceedings of the 1991 International Conference on Digital Signal Processing, Elsevier Science Publishers B.V., Amsterdam, The Netherlands (in press).
Ardizzone, E., Chella, A., Sorbello, F., A Digital Architecture Implementing the Self-Organizing Feature Maps, in: T. Kohonen, K. Makisara, O. Simula, I. Kangas (eds.), Artificial Neural Networks, ICANN-91, North-Holland, Amsterdam, 1991, pag. 721–727.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gioiello, M., Vassallo, G., Chella, A., Sorbello, F. (1991). Self-organizing maps: A new digital architecture. In: Ardizzone, E., Gaglio, S., Sorbello, F. (eds) Trends in Artificial Intelligence. AI*IA 1991. Lecture Notes in Computer Science, vol 549. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-54712-6_250
Download citation
DOI: https://doi.org/10.1007/3-540-54712-6_250
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54712-9
Online ISBN: 978-3-540-46443-3
eBook Packages: Springer Book Archive