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
Not verified in gameWhich variables this event was proposed to move, and in which direction. The magnitudes are held in the corpus but are not shown here, because they have not been verified against the shipped game. They come from pdoom-data. They describe what an event was proposed to do, not what the shipped game does with it. Most events in the corpus are flavour: they are shown for colour and do not move any game variable. Only a small minority reach the systems below, and several of the variables listed here are not read by the game at all yet. Treat this table as a design proposal under review, not as a measurement of play. Corrections and arguments are welcome — the suggestion links at the foot of this page go straight to the data repo.
| Variable | Direction | Condition |
|---|---|---|
| Research | proposed: up | Always |
| Papers | proposed: up | Always |
| Vibey Doom | proposed: up | Always |
💭 Reactions
"Notable work on AI safety"
"Published in academic venue"
🔗 Sources
🤝 Found an Issue?
This event data is sourced from the pdoom-data repository. If you notice errors or want to suggest improvements:
GitHub Issue (Preferred) 📧 Email (No GitHub)