Using Visual Analytics to Interpret Predictive Machine Learning Models
Machine Learning
2016-06-22 v2 Machine Learning
Abstract
It is commonly believed that increasing the interpretability of a machine learning model may decrease its predictive power. However, inspecting input-output relationships of those models using visual analytics, while treating them as black-box, can help to understand the reasoning behind outcomes without sacrificing predictive quality. We identify a space of possible solutions and provide two examples of where such techniques have been successfully used in practice.
Cite
@article{arxiv.1606.05685,
title = {Using Visual Analytics to Interpret Predictive Machine Learning Models},
author = {Josua Krause and Adam Perer and Enrico Bertini},
journal= {arXiv preprint arXiv:1606.05685},
year = {2016}
}
Comments
presented at 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), New York, NY