The Mythos of Model Interpretability

The Mythos of Model Interpretability
复制标题

DOI:
10.1145/3233231
复制
发表时间:
2018-10-01
影响因子:
22.7
通讯作者:
Lipton, Zachary C.
Lipton, Zachary C.
中科院分区:
计算机科学3区
文献类型:
--
作者:
Lipton, Zachary C.

文献摘要

被引文献

相似文献

有监督的机器学习模型拥有卓越的预测能力。你能相信你的模型吗?它会在部署中发挥作用吗?它还能告诉你关于这个世界的什么?
Supervised machine-learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world?