ExamGecko
Search Search Login
Home Home / Huawei / H13-311_V3.5
Question list
Search
Search

List of questions

Search
Open VPLUS File
Convert VPLUS to PDF

Related questions

In a hyperparameter-based search, the hyperparameters of a model are searched based on the data on and the model's performance metrics.
Which of the following statements are true about the k-nearest neighbors (k-NN) algorithm?
Which of the following is NOT a commonly used AI computing framework?
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)
AI inference chips need to be optimized and are thus more complex than those used for training.
When you use MindSpore to execute the following code, which of the following is the output? python Copy code x = Tensor(np.array([[1, 2], [3, 4]]), dtype.int32) x.dtype
DRAG DROP Correctly connect the layers in the architecture of an Ascend AI Processor.
Which of the following are common gradient descent methods?
In MindSpore, mindspore.nn.Conv2d() is used to create a convolutional layer. Which of the following values can be passed to this API's 'pad_mode' parameter?
Which of the following are covered by Huawei Cloud EIHealth?

Question 1 - H13-311_V3.5 discussion

Report
Export

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?

A.
Early stopping
Answers
A.
Early stopping
B.
Adjusting an activation function
Answers
B.
Adjusting an activation function
C.
Saving model parameters
Answers
C.
Saving model parameters
D.
Monitoring loss values during training
Answers
D.
Monitoring loss values during training
Suggested answer: A, C, D

Explanation:

In MindSpore, callbacks can be used in various scenarios such as:

Early stopping: To stop training when the performance plateaus or certain criteria are met.

Saving model parameters: To save checkpoints during or after training using the ModelCheckpoint callback.

Monitoring loss values: To keep track of loss values during training using LossMonitor, allowing interventions if necessary.

Adjusting the activation function is not a typical use case for callbacks, as activation functions are usually set during model definition.

Show Answer
asked 26/09/2024
Thomas Kincer
39 questions
NextNext
User
Your answer:
0 comments
Sorted by

Leave a comment first

ExamGecko

Copyright @2023 ExamGecko | All right reserved

Mail us: [email protected]
About us
Contact us
Twitter X
Facebook
Medium
Convert VPLUS to PDF
Open VPLUS files Easily and Quickly
Privacy Policy
Disclaimer
Terms