IBM C1000-059 Exam Practice Test Instant Access

Question 1

What statement is true about UTF-8?

AIt is encoding for Latin script.

BIt is rarely used today.

CIt is encoding for Unicode characters.

DIt is equal to ASCII.

Answer : C

-what-is-encoding

Question 2

Which two statements are correct about deploying machine learning models? (Choose two.)

AIt allows integration within business applications.

BIt makes it possible to create reports for management dynamically using specific parameters from executives.

CIt is critical for achieving high accuracy in training.

DIt is a necessary step in training and evaluating the performance of the models.

EIt is only possible on the cloud because they require a large amount of compute resources.

Answer : C, D

Question 3

A new test to diagnose a disease is evaluated on 1152 people, and 106 people have the disease, and 1046 people do not have the disease. The test results are summarized below:

In this sample, how many cases are false positives and false negatives?

A33 false positives and 81 false negatives

B81 false positives and 73 false negatives

C73 false positives and 81 false negatives

D81 false positives and 33 false negatives

Answer : A

Question 4

What is the goal of the backpropagation algorithm?

Ato randomize the trajectory of the neural network parameters during training

Bto smooth the gradient of the loss function in order to avoid getting trapped in small local minimas

Cto scale the gradient descent step in proportion to the gradient magnitude

Dto compute the gradient of the loss function with respect to the neural network parameters

Answer : B

Question 5

A neural network is composed of a first affine transformation (affine1) followed by a ReLU non-linearity, followed by a second affine transformation (affine2).

Which two explicit functions are implemented by this neural network? (Choose two.)

Ay = affine1(ReLU(affine2(x)))

By = max(affine1(x), affine2(x))

Cy = affine2(ReLU(affine1(x)))

Dy = affine2(max(affine1(x), 0))

Ey = ReLU(affine1(x), affine2(x))

Answer : C, D

Question 6

With only limited labeled data available how might a neural network use case be realized?

Aby assigning random labels

Bby increasing the depth of the neural network

Cby creating random data

Dby using a customized pre-trained model

Answer : D

Question 7

Which measure can be used to show business stakeholders the likelihood that a machine learning model will generate a true prediction?

Aaccuracy

Bvariance

Cmean

Dskewness

Answer : A

IBM C1000-059 IBM AI Enterprise Workflow V1 Data Science Specialist Exam Practice Test