[Q202-Q216] 2025 Updated H13-311_V3.5 Tests Engine pdf - All Free Dumps Guaranteed! : Actual Test Materials : http://blog.actualtests4sure.com

Q202. On-Device Execution, that is, the entire image is offloaded and executed, and the computing power of the Yiteng chip can be fully utilized, which can greatly reduce the interaction overhead, thereby increasing the accelerator occupancy rate.
On-Device The following description is wrong?

MindSpore Realize decentralized autonomy through adaptive graph optimization driven by gradient data A11 Reduce, Gradient aggregation is in step, and calculation and communication are fully streamlined

Challenges of model execution under super chip computing power: Memory wall problems, high interaction overhead, and difficulty in data supply. Partly in Host Executed, partly in Device Execution, interaction overhead is even much greater than execution overhead, resulting in low accelerator occupancy

MindSpore Through the chip-oriented depth map optimization technology, the synchronization wait is less, and the “data computing communication” is maximized. The parallelism of “trust”, compared with training performance Host Side view scheduling method is flat

The challenge of distributed gradient aggregation under super chip computing power:ReslNet50 Single iteration 20ms Time will be generated The synchronization overhead of heart control and the communication overhead of frequent synchronization. Traditional methods require 3 Synchronization completed A11 Reduce, Data-driven method autonomy A11 Reduce, No control overhead

Q203. Regarding the convolutional neural network pooling layer, the following description is correct?

Pooling operation is realized by scanning window

The pooling layer can play a role in dimensionality reduction

Commonly used pooling methods include maximum pooling and average pooling

The pooled feature image becomes smaller

Q204. Which of the following does the convolutional neural network structure not include?

Convolutional layer

Pooling layer

Loop layer

Fully connected layer

Q205. Which of the following are the characteristics of the Python language? {Multiple choice)

Explanatory

Process oriented

Object-oriented

Dynamic data type

Q206. Regularization is an important and effective technique for reducing generalization errors in traditional machine learning. The following techniques are regular.
The technology is:

L1 Regularization

L2 Regularization

Dropout

Momentum optimizer

Q207. Google proposed the concept of knowledge graph and took the lead in applying knowledge graphs to search engines in 2012, successfully improving users’ search quality and experience.

TRUE

FALSE

Q208. TensorFlow is Google’s first generation of proprietary machine learning systems

True

False

Q209. The matrix produced by the exchange of matrix A rows and columns is called the transpose of A.
What are the correct properties of matrix transposition? (Multiple Choice)

(A T ) T = A

(A+ 8) T = AT +BT

(!EA) T = !EAT

(AB} T = A T +BT

Q210. In the deep learning network, the backpropagation algorithm is used to find the optimal parameters. What rules are used in the backpropagation algorithm to obtain the derivation layer by layer?

Chain rule

Cumulative rule

Law of reciprocity

Rule of Normalization

Q211. In deep learning tasks, when encountering data imbalance problems, which of the following methods can we use to solve the problem?

batch deletion

Random oversampling

Synthetic sampling

Random undersampling

Q212. Recurrent neural networks can capture dynamic information in serialized data.

TRUE

FALSE

Q213. PyTorch All existing versions support Python2 with Python3?

TRUE

FALSE

Q214. 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?

pad

same

valid

nopadding

Q215. In polynomial regression, there is a square term in the formula of the model, so it is not linear.

TRUE

FALSE

Q216. The loss function reflects the error between the target output and actual output of the neural network.
The commonly used loss function in deep learning is:

Exponential loss function

Mean square loss function

Log loss function

Hinge Loss function