Fault-tolerance of basis function networks using tensor product stabilizers
Eickhoff R, Rückert U (2005)
In: Systems, Man and Cybernetics, 2005 IEEE International Conference on., 3. IEEE: 2144-2149.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Eickhoff, R.;
Rückert, UlrichUniBi
Abstract / Bemerkung
Neural networks are intended to be used in future
nanoelectronics since these architectures seem to be
fault-tolerant to malfunctioning elements and robust to noise.
In this paper, the robustness to noise of Basis Function networks
using tensor product stabilizers is analyzed and upper
bounds of the mean square error under noise contaminated
weights or inputs are determined. Furthermore, consequences
of permanently malfunctioning neurons are investigated
and their impact on the mean squared error is analyzed.
To achieve a reliable operation of the neural network
necessary restrictions are introduced. Finally, the impact
of technical realizations is investigated and its complexity is
compared to Radial Basis Functions.
Stichworte
mean square error methods;
logic testing;
fault tolerance;
tensor product stabilizers;
noise contaminated weights;
basis function networks fault-tolerance;
nanoelectronics;
tensors;
mean square error;
radial basis function networks
Erscheinungsjahr
2005
Titel des Konferenzbandes
Systems, Man and Cybernetics, 2005 IEEE International Conference on
Band
3
Seite(n)
2144-2149
ISBN
0780392981
Page URI
https://pub.uni-bielefeld.de/record/2286007
Zitieren
Eickhoff R, Rückert U. Fault-tolerance of basis function networks using tensor product stabilizers. In: Systems, Man and Cybernetics, 2005 IEEE International Conference on. Vol 3. IEEE; 2005: 2144-2149.
Eickhoff, R., & Rückert, U. (2005). Fault-tolerance of basis function networks using tensor product stabilizers. Systems, Man and Cybernetics, 2005 IEEE International Conference on, 3, 2144-2149. IEEE. https://doi.org/10.1109/ICSMC.2005.1571466
Eickhoff, R., and Rückert, Ulrich. 2005. “Fault-tolerance of basis function networks using tensor product stabilizers”. In Systems, Man and Cybernetics, 2005 IEEE International Conference on, 3:2144-2149. IEEE.
Eickhoff, R., and Rückert, U. (2005). “Fault-tolerance of basis function networks using tensor product stabilizers” in Systems, Man and Cybernetics, 2005 IEEE International Conference on, vol. 3, (IEEE), 2144-2149.
Eickhoff, R., & Rückert, U., 2005. Fault-tolerance of basis function networks using tensor product stabilizers. In Systems, Man and Cybernetics, 2005 IEEE International Conference on. no.3 IEEE, pp. 2144-2149.
R. Eickhoff and U. Rückert, “Fault-tolerance of basis function networks using tensor product stabilizers”, Systems, Man and Cybernetics, 2005 IEEE International Conference on, vol. 3, IEEE, 2005, pp.2144-2149.
Eickhoff, R., Rückert, U.: Fault-tolerance of basis function networks using tensor product stabilizers. Systems, Man and Cybernetics, 2005 IEEE International Conference on. 3, p. 2144-2149. IEEE (2005).
Eickhoff, R., and Rückert, Ulrich. “Fault-tolerance of basis function networks using tensor product stabilizers”. Systems, Man and Cybernetics, 2005 IEEE International Conference on. IEEE, 2005.Vol. 3. 2144-2149.
Google Scholar
ISBN Suche