'Today's speech processing technology can achieve a recognition accuracy of over 90% in any case.' Which of the following is true about this statement?

This statement is incorrect. In many situations, noise and background sound have a huge impact on speech recognition accuracy.

This statement is incorrect. The accuracy of speech recognition is high, but not extremely high.

This statement is incorrect. In many situations, noise and background sound have a huge impact on speech recognition accuracy.

This statement is correct. Speech processing can achieve a high level of accuracy.

This statement is correct. Speech processing has a long history and the technology is very mature.

'AI application fields include only computer vision and speech processing.' Which of the following is true about this statement?

This statement is false. The application fields of AI include computer vision, speech processing, natural language processing, and others.

This statement is false. AI application fields include only computer vision and natural language processing.

This statement is true. Voice data is processed with extremely high accuracy.

This statement is true. Computer vision is the most important AI application.

Which of the following are common gradient descent methods?

Mini-batch gradient descent (MBGD)

Stochastic gradient descent (SGD)

Mini-batch gradient descent (MBGD)

Multi-dimensional gradient descent (MDGD)

Stochastic gradient descent (SGD)

Which of the following statements are true about the k-nearest neighbors (k-NN) algorithm?

k-NN typically uses the majority voting method to predict classification.

The k-NN algorithm determines which class an object belongs to based on the class to which most of the object's k nearest neighbors belong.

k-NN typically uses the mean value method to predict regression.

k-NN typically uses the majority voting method to predict classification.

k-NN is a parametric method often used for datasets with regular decision boundaries.

The k-NN algorithm determines which class an object belongs to based on the class to which most of the object's k nearest neighbors belong.

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

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

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

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

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

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

Which of the following statements about datasets are true?

Testing refers to a process that uses a trained model for prediction. The dataset, which is used for testing, is called a testing set, and each sample is called a test sample.

A dataset generally has multiple dimensions. In each dimension, events or attributes that reflect the performance or nature of a sample in a particular aspect are called features.

In machine learning, a dataset is generally divided into a training set, validation set, and test set.

Testing refers to a process that uses a trained model for prediction. The dataset, which is used for testing, is called a testing set, and each sample is called a test sample.

A dataset generally has multiple dimensions. In each dimension, events or attributes that reflect the performance or nature of a sample in a particular aspect are called features.

In machine learning, a dataset is generally divided into a training set, validation set, and test set.

When it comes to the machine learning process, the validation set and the test set are essentially the same.

Which of the following statements are true about decision trees?

The common decision tree algorithms include ID3, C4.5, and CART.

Building a decision tree means selecting feature attributes and determining their tree structure.

A key step to building a decision tree involves dividing all feature attributes and comparing the purity of the division's result sets.

The common decision tree algorithms include ID3, C4.5, and CART.

Quantitative indicators of purity can only be obtained by using information entropy.

Building a decision tree means selecting feature attributes and determining their tree structure.

A key step to building a decision tree involves dividing all feature attributes and comparing the purity of the division's result sets.

The global gradient descent, stochastic gradient descent, and batch gradient descent algorithms are gradient descent algorithms. Which of the following is true about these algorithms?

The convergence process of the global gradient algorithm is time-consuming.

The batch gradient algorithm can solve the problem of local minimum value.

The global gradient algorithm can find the minimum value of the loss function.

The stochastic gradient algorithm can find the minimum value of the loss function.

The convergence process of the global gradient algorithm is time-consuming.

Which of the following are use cases of generative adversarial networks?

Generating a 3D model from a 2D image

Huawei H13-311_V3.5 Practice Test 1 - Free Online Exam Prep & Questions

Question 1 / 40

When learning the MindSpore framework, John learns how to use callbacks and wants to use it for AI model training. For which of the following scenarios can John use the callback?

Early stopping

Adjusting an activation function

Saving model parameters

Monitoring loss values during training

Comment (0)

Huawei H13-311_V3.5 Practice Test 1

Question

Huawei H13-311_V3.5 Practice Tests

Practice Tests