Free H13-311 Exam Dumps Preview

Question 1

Single choice

Which of the following statements is false about the debugging and application of a regression model?

1. A

   If the model does not meet expectations, you need to use data cleansing and feature engineering.

2. B

   After model training is complete, you need to use the test dataset to evaluate your model so that its
   generalization capability meets expectations.

3. C

   If overfitting occurs, you can add a regularization term to the Lasso or ridge regression and adjust hyperparameters.

4. D

   If underfitting occurs, you can use a more complex regression model, for example, logistic regression.

Reveal answer details Close answer details

Correct answerD

Question 2

Single choice

In ModelArts, which of the following can be used to automate model training and deployment?

1. A

   Workflow

2. B

   TensorBoard

3. C

   MindInsight

4. D

   Ascend Studio

Reveal answer details Close answer details

Correct answerA

Question 3

Multiple choice

Which of the following are common gradient descent methods?

1. A

   Batch gradient descent (BGD)

2. B

   Mini-batch gradient descent (MBGD)

3. C

   Multi-dimensional gradient descent (MDGD)

4. D

   Stochastic gradient descent (SGD)

Reveal answer details Close answer details

Correct answersA, B, D

Question 4

Multiple choice

Which of the following are feedforward neural networks?

1. A

   Fully-connected neural networks

2. B

   Recurrent neural networks

3. C

   Boltzmann machines

4. D

   Convolutional neural networks

Reveal answer details Close answer details

Correct answersA, D

Question 5

Single choice

In machine learning, which of the following inputs is required for model training and prediction?

1. A

   Neural network

2. B

   Historical data

3. C

   Training algorithm

4. D

   Manual program

Reveal answer details Close answer details

Correct answerB

Question 6

Single choice

Which of the following is the order of tensor [[0,1],[2,3]]?

1. A

   6

2. B

   3

3. C

   2

4. D

   4

Reveal answer details Close answer details

Correct answerC

Question 7

Single choice

AI chips, also called AI accelerators, optimize matrix multiplication.

1. A

   TRUE

2. B

   FALSE

Reveal answer details Close answer details

Correct answerA

Question 8

Single choice

An algorithm of unsupervised learning classifies samples in a dataset into several categories. Samples belonging to the same category have high similarity.

1. A

   TRUE

2. B

   FALSE

Reveal answer details Close answer details

Correct answerA

Question 9

Single choice

When you use MindSpore to execute the following code, which of the following is the output?

from mindspore import ops

import mindspore

shape = (2, 2)

ones = ops.Ones()

output = ones(shape, dtype=mindspore.float32)

print(output)

1. A

   [[1 1]
   [1 1]]

2. B

   [[1. 1.]
   [1. 1.]]

3. C

   1

4. D

   [[1. 1.
   1. 1.]]

Reveal answer details Close answer details

Correct answerB

Question 10

Single choice

AI model evaluation commonly uses which of the following metrics?

1. A

   Precision

2. B

   Recall

3. C

   F1 Score

4. D

   All of the above

Reveal answer details Close answer details

Correct answerD

Question 11

Single choice

In MindSpore, the basic unit of the neural network is nn.Cell.

1. A

   TRUE

2. B

   FALSE

Reveal answer details Close answer details

Correct answerA