Explaining a prediction in some nonlinear models
Machine Learning
2022-07-26 v4 Machine Learning
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.
Keywords
Cite
@article{arxiv.1904.09615,
title = {Explaining a prediction in some nonlinear models},
author = {Cosimo Izzo},
journal= {arXiv preprint arXiv:1904.09615},
year = {2022}
}
Comments
This paper has been withdrawn by the author as it misses a relevant part of the literature