Question 1

Which of the following options BEST describes a deep neural net?

Options :

A : It is made up several layers with each layer (except input and output layers) connected to each other layer and errors are propagated backwards through the network

B : It is comprised of a hierarchical structure of neurons with the lowest (deepest) neurons making most of the decisions

C : It is made up of layers of neurons, each of which generates an activation value based on the other neurons in the same layer

D : It is comprised of connected neurons where each neuron has an associated bias and each connection has an associated weight

Answer: D

Question 2

Which of the following options is MOST likely to be relevant when testing a system’s autonomy?

Options :

A : Testing how quickly the system can adapt

B : Testing the accuracy of system predictions

C : Testing over a sustained period of time

D : Static analysis of training data

Answer: C

Question 3

DataSure is a start-up with a product that promises to improve the quality of ML models. DataSure claim that this improvement comes from checking if the data has been labeled correctly.

Which of the following defects is MOST likely to have been prevented by using this product?

Options :

A : The model will have poor accuracy

B : The model will not fulfill its intended function

C : The model will have security vulnerabilities

D : The model will produce biased outputs

Answer: A

Question 4

Which ONE of the following models BEST describes a way to model defect prediction by looking at the history of bugs in modules by using code quality metrics of modules of historical versions as input? SELECT ONE OPTION

Options :

A : Identifying the relationship between developers and the modules developed by them.

B : Search of similar code based on natural language processing.

C : Clustering of similar code modules to predict based on similarity.

D :

Using a classification model to predict the presence of a defect by using code quality metrics as the input data.

Answer: D

Question 5

Biases introduce the chance of getting unwanted output from ML systems. Testing for biases allows the identification of errors and causal defects that can further help review datasets and remove unwanted biases.Which ONE among the following options is not a bias in AI based systems?

Options :

A : Algorithmic bias

B : Sample bias

C : Autonomous bias

D : Inappropriate bias

Answer: C

Confidently Practice Online with Free CT-AI_v1.0_World Exam Cram

Buying Options: