MODELING OF COMPONENT FAILURE IN NEURAL NETWORKS FOR ROBUSTNESS EVALUATION - AN APPLICATION TO OBJECT EXTRACTION

An investigation on the robustness (or ruggedness) of neural network ( NN) based information processing systems with respect to component fai lure (damaging of nodes/links) is done. The damaging/component failure process has been modeled as a Poisson process, To choose the instants or moments of damaging, statistical sampling technique is used, The n odes/links to be damaged are determined randomly. As an illustration, the model is implemented and tested on different object extraction alg orithms employing Hopfield's associative memory model, Gibbs random fi elds, and a self-organizing multi-layer neural network, The performanc e (hence robustness of the underlying network model) of these algorith ms is evaluated in terms of percentage of pixels correctly classified under different noisy environments and different degrees and sequences of damaging, The deterioration in the output is seen to be very small even when a large number of nodes/links are damaged.