Robustness of Radial Basis Functions

Eickhoff R, Rückert U (2006)
Neurocomputing 70(16-18): 2758-2767.

Konferenzbeitrag | Veröffentlicht| Englisch
 
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Autor/in
Eickhoff, Ralf; Rückert, UlrichUniBi
Abstract / Bemerkung
Neural networks are intended to be used in future nanoelectronic technology since these architectures seem to be robust to malfunctioning elements and noise in its inputs and parameters. In this work, the robustness of radial basis function networks is analyzed in order to operate in noisy and unreliable environment. Furthermore, upper bounds on the mean square error under noise contaminated parameters and inputs are determined if the network parameters are constrained. To achieve robuster neural network architectures fundamental methods are introduced to identify sensitive parameters and neurons.
Erscheinungsjahr
2006
Band
70
Ausgabe
16-18
Seite(n)
2758-2767
Konferenz
3rd International Work-Conference on Artificial Neural Networks (IWANN 2005)
ISSN
0925-2312
Page URI
https://pub.uni-bielefeld.de/record/2285694

Zitieren

Eickhoff R, Rückert U. Robustness of Radial Basis Functions. Neurocomputing. 2006;70(16-18):2758-2767.
Eickhoff, R., & Rückert, U. (2006). Robustness of Radial Basis Functions. Neurocomputing, 70(16-18), 2758-2767. doi:10.1016/j.neucom.2006.04.012
Eickhoff, R., and Rückert, U. (2006). Robustness of Radial Basis Functions. Neurocomputing 70, 2758-2767.
Eickhoff, R., & Rückert, U., 2006. Robustness of Radial Basis Functions. Neurocomputing, 70(16-18), p 2758-2767.
R. Eickhoff and U. Rückert, “Robustness of Radial Basis Functions”, Neurocomputing, vol. 70, 2006, pp. 2758-2767.
Eickhoff, R., Rückert, U.: Robustness of Radial Basis Functions. Neurocomputing. 70, 2758-2767 (2006).
Eickhoff, Ralf, and Rückert, Ulrich. “Robustness of Radial Basis Functions”. Neurocomputing 70.16-18 (2006): 2758-2767.