Question 1

When performing testing of a trained model, an ML engineer found that the model was highly accurate when evaluated with validation data but that it performed poorly with independent test data.

Which of the following options is MOST likely to cause this situation?

Options :

A : Poor acceptance criteria

B : Underfitting

C : Overfitting

D : Concept drift

Answer: C

Question 2

Given the following explanation about Flexibility and adaptability (I-IV):

I. Flexibility is considered to be the ability of the system to be used in situations that were not part of the original system requirements.

II. Flexibility is considered to be the ease with which the system can be modified for new situations, such as different hardware and changing operational environments.

III. Adaptability is considered to be the ease with which the system can be modified for new situations, such as different hardware and changing operational environments.

IV. Adaptability is considered to be the ability of the system to be used in situations that were not part of the original system requirements.

Which of the following statements is MOST likely to be true about Flexibility and adaptability?

Options :

A : II and IV

B : II and III

C : I and IV

D : I and III

Answer: D

Question 3

Which of the following options would MOST likely be a reason for poor labeling of data?

Options :

A : Translation errors

B : Insufficient data

C : Algorithm chosen for the ML model

D : Synthetic data

Answer: A

Question 4

The choice of ML framework, algorithm, and hyperparameters is critical as a requisite to a better system. The choice of the parameters should be as close to optimal as possible.

Which test level for AI-based systems ensure the BEST ML framework and hyperparameters are integrated with other features and components?

Options :

A : Component integration testing

B : ML Model Testing

C : Component testing

D : System testing

Answer: B

Question 5

What is the correct definition of the term "adversarial attack"?

Options :

A : The output of an activation function of a neuron in a neural network

B : The formula associated with a neuron in a neural network that determines the output of the neuron from the inputs to the neuron

C : The deliberate use of adversarial examples to cause an ML model to fail

D : The situation when a previously labelled AI system is no longer considered to be AI as technology advances

Answer: C