METHOD OF VERYFING PRETRAINED NEURAL NET MAPPING FOR USE IN SAFETY-CRITICAL SOFTWARE

摘要

A method of verifying pretrained, static, feedforward neural network mapping software using Lipschitz constants for determining bounds on output values and estimation errors is disclosed. By way of example, two cases of interest from the point of view of safety-critical software, like aircraft fuel gauging systems, are discussed. The first case is the simpler case of when neural net mapping software is trained to replace look-up table mapping software. A detailed verification procedure is provided to establish functional equivalence of the neural net and look-up table mapping functions on the entire range of inputs accepted by the look-up table mapping function. The second case is when a neural net is trained to estimate the quantity of interest from the process (such as fuel mass, for example) from redundant and noisy sensor signals. Given upper and lower bounds on sensor noises and on modeling inaccuracies, it is demonstrated how to verify the performance of such a neural network estimator ("a black box") when compared to a true value of the estimated quantity.