Sensitivity to errors in artificial neural networks: a behavioral approach

摘要

The problem of sensitivity to errors in artificial neural networks is discussed here considering an abstract model of the network and the errors that can affect a neuron's computation. Feed-forward multilayered networks are considered; the performance taken into account with respect to error sensitivity is their classification capacity. The final aim is evaluation of the probability that a single neuron's error will affect both its own classification capacity and that of the whole network. A geometrical representation of the neural computation is adopted as the basis for such evaluation. Probability of error propagation is evaluated with respect to the single neuron's output as well as to the complete network's output. The information derived is used to evaluate, for a specific digital network architecture, the most critical sections of the implementation as far as reliability is concerned and thus to point out candidates for ad-hoc fault-tolerance policies.