Oj. Kwon et Sy. Bang, DESIGN OF FAULT-TOLERANT MULTILAYER PERCEPTRON WITH A DESIRED LEVEL OF ROBUSTNESS, Electronics Letters, 33(12), 1997, pp. 1055-1057
The definition of a fault tolerant neural network is presented. The de
finition makes it possible to design a network with a desired level of
robustness. Based on this definition, an efficient method is proposed
, called selective augmentation, which transforms a trained network in
to one that is fault tolerant against a stuck at 0 fault at the hidden
neurons. It is shown, through an example, that the resulting network
designed by the proposed method is not only fault tolerant, but also m
uch less redundant than a network designed by by uniform augmentation.