Fundamentals of testing AI-based systems · Question 50 of 60
A model for assessing complex protein structures delivers results that humans can hardly verify. Which statements are correct?
2 answers are correct. Hard
Show answer
Answer
- A The complexity of the task makes manual checks of the expected outputs impractical
- B Techniques such as metamorphic testing can verify properties without an explicit expected output for every case
Explanation
Many AI tasks are too complex for a human to simply check the result. Techniques such as A/B, back-to-back and metamorphic tests work without a fixed expected output because they compare behavior or check properties. Experts help too, but they do not always agree and are sometimes wrong.