AI and safety · Question 50 of 60
A team wants to use LIME for a safety-related AI system to make decisions traceable. What must be considered?
2 answers are correct. Hard
Show answer
Answer
- B LIME can provide insights into the reasoning
- D Such techniques are not widely available and may compromise system performance
Explanation
With safety-related systems, you need to understand why the system decides as it does. Methods such as LIME (Local interpretable model-agnostic explanations) show which inputs shaped a decision. However, they are not available everywhere, can slow the system down and do not make testing unnecessary.