DocumentCode :
447494
Title :
Fault-tolerance of basis function networks using tensor product stabilizers
Author :
Eickhoff, Ralf ; Rückert, Ulrich
Author_Institution :
Syst. & Circuit Technol., Paderborn Univ., Germany
Volume :
3
fYear :
2005
fDate :
10-12 Oct. 2005
Firstpage :
2144
Abstract :
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.
Keywords :
fault tolerance; logic testing; mean square error methods; radial basis function networks; tensors; basis function networks fault-tolerance; mean square error; nanoelectronics; noise contaminated weights; tensor product stabilizers; Circuit noise; Fault tolerance; Fault tolerant systems; Nanoelectronics; Neural networks; Neurons; Noise robustness; Tensile stress; Upper bound; Working environment noise; Basis Function networks; Neural networks; approximation; fault-tolerance; tensor product stabilizer;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man and Cybernetics, 2005 IEEE International Conference on
Print_ISBN :
0-7803-9298-1
Type :
conf
DOI :
10.1109/ICSMC.2005.1571466
Filename :
1571466
Link To Document :
بازگشت