Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems

📖 Description

Interpretable to Whom? A Role-based Model for Analyzing InterpretableMachine Learning SystemsRichard Tomsett1Dave Braines12Dan Harborne2Alun Preece2Supriyo Chakraborty3AbstractSeveral researchers have argued that a machinelearning system?s interpretability should be de-?ned in relation to a speci?c agent or task: weshould not ask if the system is interpretable, butto whomis it interpretable. We describe a modelintended to help answer this question, by identify-ing different roles that agents can ful?ll in relationto the machine learning system. We illustrate theuse of our model in a variety of scenarios, ex-ploring how an agent?s role in?uences its goals,and the implications for de?ning interpretability.Finally, we make suggestions for how our modelcould be useful to interpretability researchers, sys-tem developers, and regulatory bodies auditingmachine learning systems.1. Introduction?Interpretability? is a current hot topic in machine learningresearch. The increasing complexity of...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1806.07552