wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Recap Deep Learning CNN

Total questions: 8

Worksheet time: 5mins

Name
Class
Date
1.

An image histogram represents:

a)

The distribution of pixel intensities

b)

The overall resolution of the image

c)

The number of colors used in the image

d)

The brightness of the image

2.

For an image recognition problem (recognizing the type of defect on a microcontroller), which architecture of neural network would be better suited to solve the problem?

a)

Multi Layer Perceptron

b)

Convolutional Neural Network

c)

Recurrent Neural network

d)

Perceptron

3.

Which of the following is a data augmentation technique used in image recognition tasks?

a)

Horizontal flipping

b)

Random cropping

c)

Random scaling

d)

Color jittering

4.

In Transfer Learning, when fine-tuning a pre-trained model, which layer is typically trained while keeping the rest frozen?

a)

The input layer

b)

The convolutional layers

c)

The fully connected layers

d)

The activation layers

5.

Which of the following CNN architectures is considered one of the state-of-the-art models for image classification tasks due to its deep layers and efficiency?

a)

LeNet-5

b)

AlexNet

c)

VGGNet

d)

ResNet

6.

What is the key advantage of single-stage object detection models compared to two-stage

models?

a)

Two-stage models require less training data

b)

Single-stage models are faster

c)

Single-stage models are more accurate

d)

Two-stage models are more robust to occlusion

7.

Which of the following options can be used to reduce overfitting in deep learning models?

a)

Add more data

b)

Use architecture that generalizes well

c)

Add regularization

d)

Increase architectural complexity

8.

Why are activation functions used in neural networks?

a)

To introduce non-linearity into the model

b)

To increase the size of the input data

c)

To normalize the output to zero

d)

To make the model linear and simple