Worst case analysis of weight inaccuracy effects in multilayer perceptrons

We derive a method for the analysis of weight quantization effects in multilayer perceptrons based on the application of interval arithmetic. Differently from previous results, we find worst case bounds on the errors due to weight quantization, that are valid for every distribution of the input or weight values. Given a trained network, our method allows us to easily compute the minimum number of bits needed to encode its weights.