2000 character limit reached
Explaining a prediction in some nonlinear models (1904.09615v4)
Published 21 Apr 2019 in cs.LG and stat.ML
Abstract: In this article we will analyse how to compute the contribution of each input value to its aggregate output in some nonlinear models. Regression and classification applications, together with related algorithms for deep neural networks are presented. The proposed approach merges two methods currently present in the literature: integrated gradient and deep Taylor decomposition. Compared to DeepLIFT and Deep SHAP, it provides a natural choice of the reference point peculiar to the model at use.