BriefGPT.xyz
Jun, 2019
使用受限对抗样本解释深度学习模型
Explaining Deep Learning Models with Constrained Adversarial Examples
HTML
PDF
Jonathan Moore, Nils Hammerla, Chris Watkins
TL;DR
研究机器学习算法的解释性问题，提出通过生成反事实的解释来描述不同的结果，并介绍了一种名为“Constrained Adversarial Examples”的新方法，该方法可以用于实际应用，包括处理分类属性和范围约束等领域的限制。
Abstract
machine learning
algorithms generally suffer from a problem of
explainability
. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an inf
→