QUESTION: 25

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 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.

Answer(s): D

Explanation:

The global gradient descent algorithm evaluates the gradient over the entire dataset before each update, leading to accurate but slow convergence, especially for large datasets. In contrast, stochastic gradient descent updates the model parameters more frequently, which allows for faster convergence but with noisier updates.
While batch gradient descent updates the parameters based on smaller batches of data, none of these algorithms can fully guarantee finding the global minimum in non-convex problems, where local minima may exist.

Reference:

Huawei HCIA-AI Certification, Machine Learning Algorithms Gradient Descent Methods.

Reveal Solution Next Question

QUESTION: 26

Sigmoid, tanh, and softsign activation functions cannot avoid vanishing gradient problems when the network is deep.

TRUE
FALSE

Answer(s): A

Explanation:

Activation functions like Sigmoid, tanh, and softsign suffer from the vanishing gradient problem when used in deep networks. This happens because, in these functions, gradients become very small as the input moves away from the origin (either positively or negatively). As a result, the weights of the earlier layers in the network receive very small updates, hindering the learning process in deep networks. This is one reason why activation functions like ReLU, which avoid this issue, are often preferred in deep learning.

Reference:

Huawei HCIA-AI Certification, Deep Learning Overview Activation Functions and Vanishing Gradient Problem.

Reveal Solution Next Question

QUESTION: 27

Single-layer perceptrons and logistic regression are linear classifiers that can only process linearly separable data.

TRUE
FALSE

Answer(s): A

Explanation:

Both single-layer perceptrons and logistic regression are linear classifiers, meaning they are capable of separating data that is linearly separable. However, they cannot effectively model non-linear relationships in the data. For more complex, non-linearly separable data, multi-layer neural networks or other non-linear classifiers are required.

Reference:

Huawei HCIA-AI Certification, Machine Learning Overview Linear Classifiers.

Reveal Solution Next Question

QUESTION: 28

Nesterov is a variant of the momentum optimizer.

TRUE
FALSE

Answer(s): A

Explanation:

Nesterov Accelerated Gradient (NAG) is indeed a variant of the momentum optimizer. In the traditional momentum method, the gradient is used to adjust the direction based on the current momentum. Nesterov, on the other hand, anticipates the change in the momentum by calculating the gradient at a slightly altered position. This small adjustment leads to better convergence and more efficient optimization, especially in non-convex problems. Momentum methods and their variants like Nesterov are commonly discussed in the optimization strategies for neural networks, including frameworks such as TensorFlow, which is covered in Huawei's HCIA AI courses.

Reference:

Deep Learning Overview: Discussion of optimization algorithms, including gradient descent variants like Momentum and Nesterov.
AI Development Framework: Explains the use of Nesterov in deep learning frameworks such as TensorFlow and PyTorch.

Reveal Solution Next Question

Free H13-311_V3.5 Exam Braindumps (page: 7)

QUESTION: 25

Explanation:

Reference:

QUESTION: 26

Explanation:

Reference:

QUESTION: 27

Explanation:

Reference:

QUESTION: 28

Explanation:

Reference: