目录

1. 背景

2. 方法

2.1 概念

2.2 方法目的

2.3 方法途径

参考：

---

1. 背景

Problem：最新的机器学习或深度学习模型的有效性受限于机器向人类和用户解释它想法和行为的能力。

  However, the effectiveness of these systems will be limited by the machine’s inability to explain its thoughts and actions to human users.

Aim: 让用户user从why did you do that?到 I understand why you do that.

 意义：Explainable AI will be essential, if users are to understand, trust, and effectively manage this emerging generation of artificially intelligent partners.

2. 方法

2.1 概念

可解释机器学习，Explainable Machine Learning

2.2 方法目的

可解释机器学习的目的是让现有的高精度深度学习模型增强可解释性。

2.3 方法途径

(1) Deep Explanation

(2) Interpretable Models

Stochastic AOG有意思

(3) Model Induction

参考：

[1] Gunning, David. "Explainable artificial intelligence (xai)." Defense Advanced Research Projects Agency (DARPA), nd Web 2.2 (2017).
[2] Marcus, Gary. "The next decade in ai: four steps towards robust artificial intelligence." arXiv preprint arXiv:2002.06177 (2020).
[3] Some interesting articles and resources at Google Explainable AI site: https://cloud.google.com/explainable-ai