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.
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