QUESTION: 21

The training error decreases as the model complexity increases.

TRUE
FALSE

Answer(s): A

Explanation:

As the model complexity increases (for example, by adding more layers to a neural network or increasing the depth of a decision tree), the training error tends to decrease. This is because more complex models are able to fit the training data better, possibly even capturing noise. However, increasing complexity often leads to overfitting, where the model performs well on the training data but poorly on unseen test data.
The relationship between model complexity and performance is covered extensively in Huawei HCIA AI's discussion of overfitting and underfitting and how model generalization is affected by increasing model complexity.

Reference:

Machine Learning Overview: Explains model complexity and its effect on training and testing error curves.
Deep Learning Overview: Discusses the balance between model capacity, overfitting, and underfitting in deep learning architectures.

Reveal Solution Next Question

QUESTION: 22

Which of the following is the activation function used in the hidden layers of the standard recurrent neural network (RNN) structure?

ReLU
Softmax
Tanh
Sigmoid

Answer(s): C

Explanation:

In standard Recurrent Neural Networks (RNNs), the Tanh activation function is commonly used in the hidden layers. The Tanh function squashes input values to a range between -1 and 1, allowing the network to learn complex patterns over time by transforming the input data into non-linear patterns.
While other activation functions like Sigmoid can be used, Tanh is preferred in many RNNs for its wider range. ReLU is generally used in feed-forward networks, and Softmax is often applied in the output layer for classification problems.

Reference:

Deep Learning Overview: Describes the architecture of RNNs, highlighting the use of Tanh as the standard activation function.
AI Development Framework: Discusses the various activation functions used across different neural network architectures.

Reveal Solution Next Question

QUESTION: 23

The derivative of the Rectified Linear Unit (ReLU) activation function in the positive interval is always:

0
0.5
1
Variable

Answer(s): C

Explanation:

The Rectified Linear Unit (ReLU) activation function is defined as f(x)=max(0,x)f(x) = \max(0, x)f(x)=max(0,x). In the positive interval, where x>0x > 0x>0, the derivative of ReLU is always 1. This makes ReLU popular for deep learning networks because it helps avoid the vanishing gradient problem during backpropagation, ensuring efficient gradient flow.

Reference:

Huawei HCIA-AI Certification, Deep Learning Overview Activation Functions.

Reveal Solution Next Question

QUESTION: 24

In a fully-connected structure, a hidden layer with 1000 neurons is used to process an image with the resolution of 100 x 100.
Which of the following is the correct number of parameters?

100,000
10,000
1,000,000
10,000,000

Answer(s): C

Explanation:

In a fully-connected layer, the number of parameters is calculated by multiplying the number of input features by the number of neurons in the hidden layer. For an image of resolution 100×100=10,000100 \times 100 = 10,000100×100=10,000 pixels and a hidden layer of 1,000 neurons, the total number of parameters is 10,000×1,000=1,000,00010,000 \times 1,000 = 1,000,00010,000×1,000=1,000,000.

Reference:

Huawei HCIA-AI Certification, AI Model Structures Fully Connected Layers.

Reveal Solution Next Question

Free H13-311_V3.5 Exam Braindumps (page: 6)

QUESTION: 21

Explanation:

Reference:

QUESTION: 22

Explanation:

Reference:

QUESTION: 23

Explanation:

Reference:

QUESTION: 24

Explanation:

Reference: