95 citations · 246 across the 15 of their papers we have counts for
Showing 2019 · cs.LGShow all
2 papers · 2 filters
cs.LG2019★ 3 cited
XDeep: An Interpretation Tool for Deep Neural Networks
Fan Yang, Zijian Zhang, Haofan Wang +2
XDeep is an open-source Python package developed to interpret deep models for both practitioners and researchers. Overall, XDeep takes a trained deep neural network (DNN) as the in…
cs.LG2019★ 2 cited
Contextual Local Explanation for Black Box Classifiers
Zijian Zhang, Fan Yang, Haofan Wang +1
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the predi…