RATE meeting
April 11th
Previous meeting
Proposal 1
Proposal 2
Proposal 3
Proposal 4
Proposal 5
Proposal 3
What is a good explanation?
Benefits
-
Data scientist
Conceptual framework for evaluating explanation techniques.
-
Decision maker / Regulator / User
Can explore explanations most relevant to his task.
What factors play a role?
- Simple, accurate and generic model does not exist.
- Any explanation is a simplified model.
-
There is a difference between desiderata about the model and explanation.
- ML explanations always follow the "common effect" causal pattern (Keil, 2006).
Assumptions
What factors play a role?
Word cloud
What factors play a role?
Spreadsheet
What factors play a role?
High-level interaction
Next steps...
- Explore sub categories of high-level desiderata
(+ relations)
- Quantifiable metrics to approximate these desiderata.
- Paper?