思想与社会2016 · 分享于 Hacker News
“Why Should I Trust You?” Explaining the Predictions of Any Classifier [pdf]
探索《“Why Should I Trust You?” Explaining the Predictions of Any Classifier [pdf]》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Yemsy ·
A friend of mine died and I didn't know because of algorithms
580 赞同398 评论
Yadrian_mrd ·
It’s time for a digital protection agency
253 赞同195 评论
Yskilled ·
Interpretable Machine Learning
192 赞同23 评论
Yatg_abhishek ·
Interpretability in Machine Learning: An Overview
182 赞同46 评论
Ymath_rachel ·
Thoughts on OpenAI, reinforcement learning, and killer robots
174 赞同195 评论
Yrangerranvir ·
Introduction to Support Vector Machines in Machine Learning
166 赞同87 评论
YDim25 ·
Explainable Artificial Intelligence (XAI) Darpa Funding
134 赞同40 评论
Yjonbaer ·
War by any means: The story of DARPA
121 赞同51 评论
Ytsaprailis ·
DeepVariant: Highly Accurate Genomes with Deep Neural Networks
69 赞同13 评论
YBrajeshwar ·
No physics? No problem. AI weather forecasting is already making strides
63 赞同56 评论
Yjonbaer ·
Should Artificial Intelligence Be Regulated?
31 赞同46 评论
Ylogancg ·
LIME: Explaining the predictions of any Machine Learning classifier
5 赞同1 评论
Ykawera ·
“Why Should I Trust You?” Explaining the Predictions of Any Classifier [pdf]
3 赞同0 评论
Y__Joker ·
[pdf] Explaining the Predictions of Any Classifier
1 赞同0 评论
Ycampac ·
Explaining black box models with LIME
1 赞同0 评论
YCas9 ·
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
1 赞同1 评论