Abstract

Machine learning models fit complex algorithms to arbitrarily large datasets. These algorithms are well known to be high on performance and low on interpretability. We use interactive visualization of slices of predictor space to address the interpretability deficit; in effect opening up the black-box of machine learning algorithms, for the purpose of interrogating, explaining, validating and comparing model fits. Slices are specified directly through interaction, or using various touring algorithms designed to visit high-occupancy sections, or regions where the model fits have interesting properties. The methods presented here are implemented in the R package condvis2. Supplementary files for this article are available online.

摘要

机器学习模型适合复杂算法到任意大的数据集。众所周知，这些算法性能高，可解释性低。我们使用预测空间切片的交互式可视化来解决可解释性缺陷；实际上打开了机器学习算法的黑匣子，目的是询问、解释、验证和比较模型拟合度。切片是通过交互直接指定的，或者使用旨在访问高占用部分或模型适合具有有趣属性的区域的各种旅游算法。此处介绍的方法在 R 包 condvis2 中实现。本文的补充文件可在线获取。