Worst case analysis of weight inaccuracy effects in multilayer perceptrons
Davide Anguita, Sandro Ridella, Stefano Rovetta · IEEE Transactions on Neural Networks · 1999
We derive here a new 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 to easily compute the minimum number of bits needed to encode its weights.