目錄

1. 背景

2. 方法

2.1 概念

2.2 方法目的

2.3 方法途徑

參考：

---

1. 背景

Problem：最新的機(jī)器學(xué)習(xí)或深度學(xué)習(xí)模型的有效性受限于機(jī)器向人類(lèi)和用戶(hù)解釋它想法和行為的能力。

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

Aim: 讓用戶(hù)user從why did you do that?到 I understand why you do that.

?意義：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

可解釋機(jī)器學(xué)習(xí)，Explainable Machine Learning

2.2 方法目的

可解釋機(jī)器學(xué)習(xí)的目的是讓現(xiàn)有的高精度深度學(xué)習(xí)模型增強(qiáng)可解釋性。

2.3 方法途徑

(1) Deep Explanation

(2) Interpretable Models

Stochastic AOG有意思

(3) Model Induction

參考：

[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

?

?

?

總結(jié)

以上是生活随笔為你收集整理的机器学习应用方向(三)～可解释机器学习Explainable ML/Explainable AI的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。