Fault-Tolerance Of Associative Memories Based On Neural Networks

Rückert U, Kreuzer I, Tryba V (1989)
In: Proceedings of the International Conference on Computer Technology, Systems and Applications. Hamburg, Germany: IEEE Comput. Soc. Press: 1.52-1.55.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Rückert, UlrichUniBi; Kreuzer, I.; Tryba, V.
Abstract / Bemerkung
The authors discuss the hardware fault tolerance of associative memories. They study device parameter variations across a chip, which affect essentially the characteristics of analog circuits used by several architectures. The effects of these errors on the performance are examined by means of three typical representatives: the Hopfield model, the self-organizing feature map, and the Boltzmann machine. The authors present a worst-case estimation of the guaranteed fault tolerance of these networks and discuss the consequences for the features of the associative memories. The main result is that the fault tolerance decreases with the number of weights but can be improved by using spare codes or self-organization in connection with added resources
Erscheinungsjahr
1989
Titel des Konferenzbandes
Proceedings of the International Conference on Computer Technology, Systems and Applications
Seite(n)
1.52-1.55
ISBN
0818619406
Page URI
https://pub.uni-bielefeld.de/record/2281072

Zitieren

Rückert U, Kreuzer I, Tryba V. Fault-Tolerance Of Associative Memories Based On Neural Networks. In: Proceedings of the International Conference on Computer Technology, Systems and Applications. Hamburg, Germany: IEEE Comput. Soc. Press; 1989: 1.52-1.55.
Rückert, U., Kreuzer, I., & Tryba, V. (1989). Fault-Tolerance Of Associative Memories Based On Neural Networks. Proceedings of the International Conference on Computer Technology, Systems and Applications, 1.52-1.55. Hamburg, Germany: IEEE Comput. Soc. Press. doi:10.1109/CMPEUR.1989.93343
Rückert, U., Kreuzer, I., and Tryba, V. (1989). “Fault-Tolerance Of Associative Memories Based On Neural Networks” in Proceedings of the International Conference on Computer Technology, Systems and Applications (Hamburg, Germany: IEEE Comput. Soc. Press), 1.52-1.55.
Rückert, U., Kreuzer, I., & Tryba, V., 1989. Fault-Tolerance Of Associative Memories Based On Neural Networks. In Proceedings of the International Conference on Computer Technology, Systems and Applications. Hamburg, Germany: IEEE Comput. Soc. Press, pp. 1.52-1.55.
U. Rückert, I. Kreuzer, and V. Tryba, “Fault-Tolerance Of Associative Memories Based On Neural Networks”, Proceedings of the International Conference on Computer Technology, Systems and Applications, Hamburg, Germany: IEEE Comput. Soc. Press, 1989, pp.1.52-1.55.
Rückert, U., Kreuzer, I., Tryba, V.: Fault-Tolerance Of Associative Memories Based On Neural Networks. Proceedings of the International Conference on Computer Technology, Systems and Applications. p. 1.52-1.55. IEEE Comput. Soc. Press, Hamburg, Germany (1989).
Rückert, Ulrich, Kreuzer, I., and Tryba, V. “Fault-Tolerance Of Associative Memories Based On Neural Networks”. Proceedings of the International Conference on Computer Technology, Systems and Applications. Hamburg, Germany: IEEE Comput. Soc. Press, 1989. 1.52-1.55.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche