Sensitivity analysis of multilayer percetron based on elastic function

Chun-Guo Li, Haifeng Li, Yu-Fen Zhang, Qun-Feng Zhang

Abstract: The sensitivity analysis can help to construct a tightly neural network. There are several methods to define the sensitivity of input and weight for perturbations to the trained neural network. This paper proposed a sensitivity definition based on elastic function. This definition considers the measure of the variable of the reference network. The sensitivity calculating formulae are deduced for perceptron and MLP.