7. Which of the following points constitute a support vector of the SVM algorithm without considering regularization terms?

C. Points closest to the separating hyperplane

A. Points on the separating hyperplane

B. Farthest points from the separating hyperplane

13. Which of the following are false about convolutional neural networks?

B. Convolution kernels cannot extract global features of images.

A. A convolutional neural network may contain convolutional, pooling, and fully connected layers.

C. Common pooling includes max pooling and average pooling.

D. When an image is processed, convolution is implemented by using a scanning window.

14. Overfitting problems can be avoided through dataset expansion. Which of the following statements is true about dataset expansion?

A. The larger the dataset, the lower the probability of overfitting.

B. The larger the dataset, the higher the probability of overfitting.

C. The smaller the dataset, the lower the probability of overfitting.

D. The probability of overfitting decreases when the dataset increases or decreases.

16. Which of the following statements about the running process of the MindArmour subsystem is false?

B. Fuzzing execution: Generate trusted test data randomly based on the model coverage and configuration policies.

A. Configuration policies: Define test policies based on threat vectors and trustworthiness certification requirements and select appropriate test data generation methods.

C. Evaluation report: Generate an evaluation report based on built-in or user-defined trustworthiness metrics.

D. Trustworthiness enhancement: Use preset methods to enhance the trustworthiness of AI models.

17. Which of the following is NOT a complexity feature of AI computing?

D. Parallel processing of structured and unstructured data

C. Parallel communication and computing

18. On-device execution refers to the execution of the entire graph. It makes full use of the computing power of the Ascend AI Processor, greatly reducing the interaction overhead and improving the accelerator usage. Which of the following is false about on-device execution?

B. The chip-oriented deep graph optimization is used to reduce synchronization waiting time and maximize the parallelism degree of "data-computing-communication". The training performance is equivalent to that of the graph scheduling mode on the host.

A. Challenges to model execution with powerful chip computing power: Memory wall problems, high interaction overhead, and difficult data supply. Some operations are performed on the host, while others are performed on the device. The interaction overhead is much greater than the execution overhead. As a result, the accelerator usage is low.

C. Challenges to distributed gradient aggregation with powerful chip computing power:When a single iteration of ResNet-50 takes 20 ms, the central control overhead and communication overhead for frequent synchronization are generated. The traditional method requires three times of synchronization to complete AllReduce. The data-driven method automatically performs AllReduce without control overhead.

D. MindSpore uses gradient-driven adaptive graph optimization to implement decentralized and autonomous All Reduce. The gradient aggregation step is consistent, and computing and communication are fully streamlined.

19. Which of the following statements about the Da Vinci architecture is incorrect?

A. A compute unit contains four types of basic compute resources.

B. Control units are responsible for the running of AI Cores.

C. The storage system consists of on-chip storage units of AI Core and corresponding data paths.

D. Transfers data to the L1 buffer through the bus interface unit.

21. Which of the following statements about the L1 buffer is true?

C. The L1 buffer decreases data accesses over the bus and avoids bus congestion.

A. Data in the L1 buffer needs to be read outside the AI Core over the bus interface each time.

B. The L1 buffer can permanently retrain data that needs to be reused.

D. L1 buffer is used to store the initial values in the neural network.

23. Which of the following statements about the three major schools of AI are true?

A. Symbolicism puts more focus on logical inference. Connectionism is relatively weak in terms of being logical and interpretability. Instead, it focuses on results.

B. Connectionism stems from the study of bionics, especially human brain models.

C. Actionism puts more focus on practice. It believes in constantly adapting actions by learning from the environment.

D. Symbolicism puts more focus on practice. It believes in constantly adapting actions by learning from the environment.

25. Which of the following statements about some of AI use case are true?

A. Smart home uses technologies such as the Internet of Things (IoT) and speech recognition.

B. Smart healthcare uses AI technologies such as computer vision and data mining.

C. Smart city is a comprehensive domain, covering all three basic technology fields of AI: speech, NLP, and computer vision.

D. Smart education features openness, sharing, interaction, collaboration, and ubiquity. It aims to modernize education and upgrade traditional teaching methods with information technologies.

26. Which of the following statements about datasets are true?

A. A dataset is a collection of data used in machine learning tasks. Each piece of data is called a sample.

B. Events or attributes that reflect the performance or nature of a sample in a particular aspect are called features.

C. A training set is a dataset used in the training process, where each sample is referred to as a training sample.

D. Learning (or training) is the process of building a model from data.

27. Which of the following statements about data preprocessing are true?

A. Data cleansing is a process of filling in missing values, as well as detecting and eliminating noise data and exceptions.

B. The purpose of data dimension reduction is to simplify data attributes and avoid the curse of dimensionality.

C. The purpose of data standardization is to reduce noise data and improve model accuracy by standardizing data.

D. Machine learning outputs results through models. Therefore, model training is more important than data preprocessing.

28. Which of the following statements are true about model parameters and hyperparameters?

A. Models contain both parameters and hyperparameters.

C. Hyperparameters are manually set.

D. Hyperparameters can be used to control training.

B. Hyperparameters are automatically learned by models.

30. Which of the following statements are true about the advantages of the Rectified Linear Unit (ReLU) activation function?

C. The vanishing gradient problem can be effectively alleviated.

A. The output is bounded, meaning the training is not easy to diverge.

Huawei HCIA-AI V3.5 Demo

Authored by Yasser Mamdouh

Other

11th Grade

Used 3+ times

AI Actions

Add similar questions

Adjust reading levels

Convert to real-world scenario

Translate activity

More...

Content View
Student View

125 questions

Show all answers

OPEN ENDED QUESTION

A. For regression problems, the output variables are discrete values. For classification problems, the output variables are continuous values.

B. The most commonly used indicators for evaluating regression and classification problems are accuracy and recall rate.

C. There may be overfitting in both regression and classification problems

D. Logistic regression is a typical regression model

Access all questions and much more by creating a free account

Create resources

Host any resource

Get auto-graded reports

Continue with Google

Continue with Email

Continue with Microsoft

or continue with

Facebook

Apple

Others

By signing up, you agree to our Terms of Service & Privacy Policy

Already have an account?

Similar Resources on Wayground

130 questions

TIN AC QUY

Quiz

•

11th Grade

127 questions

Đề Cương Ôn Tập Vật Lý

Quiz

•

11th Grade

130 questions

ôn gdcd ck1

Quiz

•

11th Grade

124 questions

Câu Hỏi Trắc Nghiệm Kinh Tế

Quiz

•

11th Grade

Popular Resources on Wayground

6 questions

PRIDE Always and Everywhere

Presentation

•

12th Grade

20 questions

Lab Safety Quiz

Quiz

•

6th Grade

26 questions

KOR Review Kahoot Questions

Quiz

•

8th Grade

21 questions

Continents and Oceans

Quiz

•

6th Grade

12 questions

Unit Zero lesson 2 cafeteria

Presentation

•

9th - 12th Grade

20 questions

Parts of Speech

Quiz

•

5th Grade

10 questions

Riddles Riddles fun Riddles

Quiz

•

6th - 12th Grade

16 questions

Subject & Predicate

Quiz

•

5th Grade

Discover more resources for Other

12 questions

Unit Zero lesson 2 cafeteria

Presentation

•

9th - 12th Grade

10 questions

Riddles Riddles fun Riddles

Quiz

•

6th - 12th Grade

10 questions

Would you Rather?

Quiz

•

9th - 12th Grade

10 questions

Soup, Salad, or Sandwich?

Quiz

•

1st Grade - Professio...

10 questions

Labor Day and Its Historical Significance

Interactive video

•

7th - 12th Grade

20 questions

Scientific Method & Variables

Quiz

•

9th - 12th Grade

7 questions

EAHS PBIS Lesson- Bathroom

Presentation

•

9th - 12th Grade

20 questions

Spanish alphabet

Quiz

•

9th - 12th Grade

Huawei HCIA-AI V3.5 Demo

Name:

1. What are the levels of driving automation defined by SAE International, formerly named the Society of Automotive Engineers (SAE), based on the degree of dependency on the system?

2. Which of the following technologies is commonly used for image feature extraction and related research?

3. Data is carrier and representation of information. Which of the following statements about data in AI applications is true?

4. Consider a scenario where a machine learning algorithm is used to filter spam. According to the definition of machine learning, which of the following describes the experience E?

5. A computer uses labeled images to learn and determine which images contain apples and which contain pears. Which of the following types of machine learning is most applicable to this scenario?

6. Which of the following statements is true about classification models and regression models in machine learning?

7. Which of the following points constitute a support vector of the SVM algorithm without considering regularization terms?

8. Kernel functions allow algorithms to fit the largest hyperplane in a transformed high-dimensional feature space. Which of the following is not a common kernel function?

9. In 1958, Frank Rosenblatt invented the perceptron algorithm. 10 years later, Marvin Minsky questioned the perceptron's ability to solve non-linear classification problems, and proposed the question that signed the death warrant of perceptrons. Which of the following is the question?

Access all questions and much more by creating a free account

Similar Resources on Wayground

Popular Resources on Wayground

Discover more resources for Other