interpretability

Self-explaining DNN

2020/12/29 12:00:00 paper list survey interpretability

key words: Self-explaining models

Post-hoc interpretability

2020/12/29 12:00:00 paper list survey interpretability

研究问题描述

深度学习模型的事后（post-hoc）可解释方法：给定一个已训练的深度神经网络模型，如何对其输出进行解释。