Ethical AI Design
Explainability
An AI's ability to justify its decision by pointing to the features that led to it.
In real life
If an AI says a photo shows a wolf, an explainable system can show it looked at the snow in the background, which is a clue that it may be wrong.
Try it (2 minutes)
Make a decision, like what to eat, and explain it in three reasons. Would a friend trust your choice more after hearing them?
Talk about it
Should self-driving cars be required to explain every decision? Why?
In the game
It costs 2 Data to play, and you can put it in your Training Set. It has Capability 1 (how hard it hits) and Trust 3 (how many Flags it can take), and scores 2 Tokens each time it Runs a Task. How to play