A team has achieved 100% neuron coverage on their test set for a neural network, yet the model still misclassifies some inputs. What is the most likely reason for this?

The network has too many neurons

Neuron coverage does not guarantee that all input behaviors are tested

The activation threshold was set too low

A test team has measured that their test set achieves 100% neuron coverage on a neural network. What does this result indicate about the test set?

The test set is guaranteed to detect all faults in the network.

The test set includes at least one test case for every possible input value.

Every neuron in the network was activated at least once by the test set.

Every possible combination of neuron activations has been exercised.

A team is testing a neural network for a medical diagnosis system. They have a test set that achieves high neuron coverage, but they are concerned about the model's performance on underrepresented patient groups. What is the most appropriate action?

Retrain the model with the same data

Add test cases from underrepresented groups to the test set

Use a different coverage metric, such as k-multisection

Increase the activation threshold for coverage

A team is testing a neural network for a safety-critical application. They have achieved high neuron coverage, but they are concerned that the coverage metric may not be sufficient to ensure safety. They are considering using mutation testing as a complementary technique. What is the primary benefit of mutation testing in this context?

It generates new test inputs that activate previously inactive neurons

It increases the number of neurons in the network

It reduces the activation threshold for all neurons

It assesses the ability of the test suite to detect injected faults

Certified Tester AI Testing

Domain 6Objective 2

Coverage Measures for Neural Networks CT-AI Practice Questions (Page 1)

Part of the Domain 6: ML - Neural Networks and Testing domain, which makes up ~2% of our current practice bank. ISTQB does not publish an official question count, but from its 60-minute exam (~25–40 total, ~1–1 in this domain), expect 1–1 from this objective — we provide 14 practice questions to prepare you well beyond it. (estimate)

14questions here

3free pages

3concepts

Questions 1–5

1application · medium
A team has achieved 100% neuron coverage on their test set for a neural network, yet the model still misclassifies some inputs. What is the most likely reason for this?
Select an answer first
2foundation · easy
A test team has measured that their test set achieves 100% neuron coverage on a neural network. What does this result indicate about the test set?
Select an answer first
3application · medium
A team is testing a neural network for a medical diagnosis system. They have a test set that achieves high neuron coverage, but they are concerned about the model's performance on underrepresented patient groups. What is the most appropriate action?
Select an answer first
4foundation · easy
Which neural network coverage metric divides the range of possible activation values into multiple intervals and measures how many of those intervals are exercised by the test data?
Select an answer first
5expert · medium
A team is testing a neural network for a safety-critical application. They have achieved high neuron coverage, but they are concerned that the coverage metric may not be sufficient to ensure safety. They are considering using mutation testing as a complementary technique. What is the primary benefit of mutation testing in this context?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to CT-AI

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by ISTQB. “CT-AI” is a trademark of its owner, used for identification only.

Coverage Measures for Neural Networks CT-AI Practice Questions (Page 1)

Questions 1–5

A team has achieved 100% neuron coverage on their test set for a neural network, yet the model still misclassifies some inputs. What is the most likely reason for this?

A test team has measured that their test set achieves 100% neuron coverage on a neural network. What does this result indicate about the test set?

A team is testing a neural network for a medical diagnosis system. They have a test set that achieves high neuron coverage, but they are concerned about the model's performance on underrepresented patient groups. What is the most appropriate action?

Which neural network coverage metric divides the range of possible activation values into multiple intervals and measures how many of those intervals are exercised by the test data?

Keep studying — Domain 6: ML - Neural Networks and Testing