Lilian Weng·· 2017-08-01AI 评分22
如何解释机器学习模型的预测？
How to Explain the Prediction of a Machine Learning Model?
AI 导读
summary_zh: Lipton (2017) 在"The mythos of model interpretability"中总结可解释模型三性质：simulatability、algorithmic transparency 与 decomposability。
来源：Lilian Weng · lilianweng.github.io