Daily Quiz No. 21
Daily Quiz ISTQB CT-AI
Nine questions in a row. The clock starts with the first question, and every question gets one try.
0 of 9 answered
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
The clock starts with the first question.
How the Daily Quiz works
- Every day at midnight (German time) there are 9 new questions, the same for everyone.
- The questions come in order, from easy to hard. With the same score, time decides.
- At the end you copy one sentence with a link. Whoever opens it plays the same questions against your score.
- Some questions come from the paid levels, so every day you see what the full course holds.
Yesterday in the Daily Quiz
- Which tool is an example of explainable AI techniques?
- What does API testing check when deploying an ML system?
- What does testing of training pipelines often focus on, unlike operational pipelines?
- How do generative adversarial networks (GAN) create realistic synthetic data?
- What does the choice of ML form (supervised, unsupervised, reinforcement) depend on?
- Which mitigation helps against problems in the algorithm, model or framework that introduce systemic unfairness?
- A team chose k-fold cross-validation with an unsuitable split and considers the results reliable. Which mitigation helps against this development risk?
- In which order do the steps of training a neural network take place?
- In a dataset of election results, the vote shares of all parties in one constituency add up to 104%, although they should be exactly 100%. Which constraint detects this defect?