Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations.
Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations.
复制标题
我们学会解释了吗?:可解释性方法如何学习在其解释中编码预测。
DOI:
--
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Ranganath,Rajesh
中科院分区:
文献类型:
--
作者:
Jethani,Neil;Sudarshan,Mukund;Aphinyanaphongs,Yindalon;Ranganath,Rajesh