Robustness of radial basis functions

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 unrel...

Full description

Saved in:
Bibliographic Details
Published inNeurocomputing (Amsterdam) Vol. 70; no. 16; pp. 2758 - 2767
Main Authors Eickhoff, Ralf, Rückert, Ulrich
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.10.2007
Subjects
Equicontinuity
Nanoelectronics
Radial basis function
Robustness
Sensitivity analysis
Radial basis function
Robustness
Equicontinuity
Sensitivity analysis
Nanoelectronics
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2006.04.012