The Doctor Just Won't Accept That!

Abstract

Calls to arms to build interpretable models express a well-founded discomfort with machine learning. Should a software agent that does not even know what a loan is decide who qualifies for one? Indeed, we ought to be cautious about injecting machine learning (or anything else, for that matter) into applications where there may be a significant risk of causing social harm. However, claims that stakeholders "just won't accept that!" do not provide a sufficient foundation for a proposed field of study. For the field of interpretable machine learning to advance, we must ask the following questions: What precisely won't various stakeholders accept? What do they want? Are these desiderata reasonable? Are they feasible? In order to answer these questions, we'll have to give real-world problems and their respective stakeholders greater consideration.

Presented at NIPS 2017 Interpretable ML Symposium

Cited by in corpus (10)

• A Survey on the Explainability of Supervised Machine Learning
• How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations
• Benchmarking Deep Learning Interpretability in Time Series Predictions
• Risk of AI in Healthcare: A Comprehensive Literature Review and Study Framework
• "The Human Body is a Black Box": Supporting Clinical Decision-Making with Deep Learning
• Unexplainability and Incomprehensibility of Artificial Intelligence
• MonoNet: Towards Interpretable Models by Learning Monotonic Features
• A psychophysics approach for quantitative comparison of interpretable computer vision models
• VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models
• A Bayesian Approach to Modelling Longitudinal Data in Electronic Health Records