R. Velazco et al., ARTIFICIAL NEURAL-NETWORK ROBUSTNESS FOR ON-BOARD SATELLITE IMAGE-PROCESSING - RESULTS OF UPSET SIMULATIONS AND GROUND TESTS, IEEE transactions on nuclear science, 44(6), 1997, pp. 2337-2344
Artificial Neural Networks have been shown to possess fault tolerant p
roperties. We present the architecture of a neural network designed to
process satellite images (SPOT photos). Computer simulations and grou
nd tests performed on a digital implementation of this neural network
prove its robustness with respect to bit errors.