Unit 4 -  CNN Architecture

Unit 4 - CNN Architecture

10 Qs

quiz-placeholder

Similar activities

Topic 7 Lesson 3 Quiz

Topic 7 Lesson 3 Quiz

6th Grade

10 Qs

2nd Quarter assessment Practice age dating of rock

2nd Quarter assessment Practice age dating of rock

KG - University

14 Qs

Layers of the Earth Vocabulary Vocab Quiz Review

Layers of the Earth Vocabulary Vocab Quiz Review

6th Grade

15 Qs

8th Grade Fossil Assessment LS4-1

8th Grade Fossil Assessment LS4-1

KG - University

13 Qs

Research and Presentation Unit Test

Research and Presentation Unit Test

KG - University

10 Qs

Unit 4 -  CNN Architecture

Unit 4 - CNN Architecture

Assessment

Quiz

others

Hard

Created by

Arsanchai Sukkuea

Used 1+ times

FREE Resource

10 questions

Show all answers

1.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

What is the primary advantage of using a deeper CNN architecture with more layers?
Improved generalization and feature extraction
Reduced overfitting
Faster training times
Smaller model size

2.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

What is the purpose of the softmax activation function in the output layer of a CNN for image classification?
To introduce non-linearity
To reduce the size of the feature maps
To convert raw scores into class probabilities
To speed up training

3.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Which technique is commonly used to combat overfitting in CNNs?
Decreasing the dropout rate
Increasing the batch size
Adding more convolutional layers
Reducing the learning rate

4.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

In transfer learning using pre-trained CNN models, what are the typical ways to adapt the model to a new task?
Fine-tuning the last few layers and adding new fully connected layers
Keeping all layers frozen and adjusting the learning rate
Using the pre-trained model without any modifications
Re-training the entire model from scratch

5.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Which layer type is commonly used to capture high-level features in a CNN?
Convolutional layer
Pooling layer
Fully connected layer
Activation layer

6.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

What is the primary purpose of the ReLU (Rectified Linear Unit) activation function in CNNs?
To introduce non-linearity
To normalize the data
To convert data to binary format
To reduce the size of feature maps

7.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

In a CNN, what does the term "kernel" or "filter" refer to?
A learning rate for gradient descent
A type of pooling operation
A small window used for convolution operations
The output of a fully connected layer

Create a free account and access millions of resources

Create resources
Host any resource
Get auto-graded reports
or continue with
Microsoft
Apple
Others
By signing up, you agree to our Terms of Service & Privacy Policy
Already have an account?