BriefGPT.xyz
Oct, 2018
机器学习解释的艺术与科学
On the Art and Science of Machine Learning Explanations
HTML
PDF
Patrick Hall
TL;DR
本文讨论超越传统误差测量和图形评估机器学习模型的几种通用的解释方法，包括决策树模型、个体条件期望、局部可解释模型无关解释、偏置度量图和Shapley解释；并提供现实应用建议和公共软件示例以复现性检验。
Abstract
This text discusses several
explanatory methods
that go beyond the error measurements and plots traditionally used to assess
machine learning models
. Some of the methods are tools of the trade while others are ri
→