Techniques for Interpretable Machine Learning

TL;DR

This survey reviews existing techniques for making machine learning models more interpretable, discusses current challenges, and highlights future research directions including user-friendly explanations and evaluation metrics.

Contribution

It provides a comprehensive overview of interpretability methods and identifies key issues for advancing the field of interpretable machine learning.

Findings

Summarizes various interpretability techniques

Highlights challenges in explanation design

Suggests future research directions

Abstract

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a comprehensive understanding of the achievements and challenges is still lacking. We provide a survey covering existing techniques to increase the interpretability of machine learning models. We also discuss crucial issues that the community should consider in future work such as designing user-friendly explanations and developing comprehensive evaluation metrics to further push forward the area of interpretable machine learning.