Abstract
PDF (377 K)
E-mail Article
Add to my Quick Links
Cited By in Scopus (4)
doi:10.1016/S0004-3702(01)00053-4 
Copyright © 2001 Elsevier Science B.V. All rights reserved.
Hybrid hardware for a highly parallel search in the context of learning classifiers
M. Bode
, 
, a, O. Freyda, J. Fischera, F. -J. Niedernostheideb and H. -J. Schulzeb
a Westfälische Wilhelms-Universität Münster, Institut für Angewandte Physik, Corrensstr. 2-4, 48149 Münster, Germany
Received 18 April 2000;
Abstract
Based on a comparison of input data with a set of prototypes, classifier systems identify the most appropriate representative for a given sample pattern. One remarkable classifier is Kohonen's Self-Organizing Map and the related learning vector quantizer, as these algorithms are highly parallel. For real-time applications the classifier search may be one of the time critical processes. We discuss specialized hardware being able to execute such a search in a fully parallel manner. Also the learning and updating of prototypes is performed in parallel controlled by a propagating front. Finally, we present experimental results concerning an unsupervised learning vector quantizer (LVQ) and a self-organizing map (SOM) obtained from our thyristor-based analog-digital hybrid system.
Author Keywords: Self-organizing map; Learning vector quantizer; Unsupervised learning; Neural net hardware; Analog; Front propagation; Thyristor
References
1. M. Bode , Front-bifurcations in reaction-diffusion systems with inhomogeneous parameter distributions. Physica D 106 (1997), pp. 270–286. Abstract | 
PDF (1037 K)
| View Record in Scopus | Cited By in Scopus (21)
2. E. Erwin, K. Obermayer and K. Schulten , Self-organizing maps: Ordering, convergence properties and energy functions. Biological Cybernetics 67 (1992), pp. 47–55. View Record in Scopus | Cited By in Scopus (103)
3. P. Heim, B. Hochet and E. Vittoz , Generation of learning neighbourhood in Kohonen feature maps by means of simple nonlinear network. Electronics Letters 27 3 (1991), pp. 275–277. View Record in Scopus | Cited By in Scopus (4)
4. J. Hertz, A. Krogh and R.G. Palmer Introduction in the Theory of Neural Computation, Addison Wesley, Reading, MA (1991).
5. T. Kohonen Self-Organizing Maps, Springer, Berlin (1995).
6. D. Macq, M. Verleysen, P. Jespers and J.-D. Legat , Analog implementation of a Kohonen map with on-chip learning. IEEE Trans. on Neural Networks 4 3 (1993), pp. 456–461. View Record in Scopus | Cited By in Scopus (6)
7. J.R. Mann and S. Gilbert , An analog self-organizing neural network chip. In: D.S. Touretzky, Editor, Advances in Neural Information Processing Systems, San Mateo, CA (1989), pp. 739–747.
8. M.S. Melton, T. Phan, D.S. Reeves and D.E. van den Bout , The TInMANN VLSI chip. IEEE Trans. Neural Networks 3 (1992), pp. 375–384. View Record in Scopus | Cited By in Scopus (15)
9. S. Rüping, U. Rücking and K. Goser , A chip for self-organizing feature maps. IEEE MICRO 15 3 (1995), pp. 57–59. View Record in Scopus | Cited By in Scopus (4)
10. D. Ruwisch, M. Bode and H.-G. Purwins , Parallel hardware implementation of Kohonen's algorithm with an active medium. Neural Networks 6 (1993), pp. 1147–1157. View Record in Scopus | Cited By in Scopus (11)
11. D. Ruwisch, M. Bode, H.-J. Schulze and F.-J. Niedernostheide , Synergetic hardware concept for self-organizing neural networks. In: J. Parisi, S.C. Müller and W. Zimmermann, Editors, Nonlinear Physics of Complex SystemsLecture Notes in Physics 476, Springer, Berlin (1996), pp. 194–212.
12. H. Speckmann, P. Thole and W. Rosenstiel , COKOS: A COprocessor for KOhonen's selforganizing map. In: S. Gielen and B. Kappen, Editors, Proceedings of the International Conference on Artificial Neural Networks (ICANN93), Amsterdam (1993), pp. 1040–1044.
Corresponding author; email: bodemat@uni-muenster.de
