Explaining a prediction in some nonlinear models
arXiv:1904.09615
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.
arXiv commentThis paper has been withdrawn by the author as it misses a relevant part of the literature
References in corpus (5)
- Axiomatic Attribution for Deep Networks
- Methods for Interpreting and Understanding Deep Neural Networks
- Learning Important Features Through Propagating Activation Differences
- European Union regulations on algorithmic decision-making and a "right to explanation"
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition