sunxingen / deepexplain Goto Github PK
View Code? Open in Web Editor NEWThis project forked from marcoancona/deepexplain
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
Home Page: https://arxiv.org/abs/1711.06104
License: MIT License