Practice Bias And Fairness In Evaluation (12.9) - Evaluation Methodologies of AI Models

Practise this section

10 questions

Flashcard drill
3 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
4 questions · about 3 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What is bias in the context of AI?
Show hintHide hint
Think about how training data may be lopsided.
Question 2.
What is meant by fairness-aware metrics?
Show hintHide hint
Consider metrics that ensure everyone is treated equally.
3Question 3.
What does bias in AI usually stem from?
- Training data
- Algorithm design
- External environments
Show hintHide hint
Consider where the AI learns its information.
4Question 4.
True or False: All AI models are fair with no bias.
- True
- False
Show hintHide hint
Think about how data reflects reality.
Question 5.
Imagine you are tasked with creating a fairness-aware metric for an AI model that predicts loan approvals. Design this metric and justify your choices.
Show hintHide hint
Consider what characteristics will indicate equitable treatment across groups.
Question 6.
Reflect on a popular case where AI bias has negatively impacted a community. Discuss how you might redesign the training data to rectify such bias.
Show hintHide hint
Think about the variety of people included in training samples.

6 more questions in this section. Enroll free to practise them all.