DESIGN OF FAULT-TOLERANT MULTILAYER PERCEPTRON WITH A DESIRED LEVEL OF ROBUSTNESS

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.