LGAIMLJul 31, 2018

Techniques for Interpretable Machine Learning

arXiv:1808.00033v31226 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental survey paper that synthesizes existing work for researchers and practitioners in interpretable machine learning.

The paper provides a survey of existing techniques to increase the interpretability of machine learning models, addressing the problem that humans cannot understand complex model behaviors and decisions, and discusses future challenges like user-friendly explanations and evaluation metrics.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes