BriefGPT.xyz
Jun, 2017
模型提取实现可解释性
Interpretability via Model Extraction
HTML
PDF
Osbert Bastani, Carolyn Kim, Hamsa Bastani
TL;DR
这篇论文提出一种名为模型抽取的方法,通过构建一个可解释程度更高的模型来近似黑箱模型,从而理解和调试机器学习模型在各种数据集上训练的结果,并在经典强化学习问题中学习控制策略。
Abstract
The ability to interpret
machine learning
models has become increasingly important now that
machine learning
is used to inform consequential decisions. We propose an approach called
→