wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Week4_S1_C2

Total questions: 10

Worksheet time: 5mins

Name
Class
Date
1.

CNNs were originally inspired by the structure of the (a)  

2.

Which CNN component is responsible for detecting patterns like edges and shapes?

a)

Fully connected layers

b)

Pooling layers

c)

Convolutional filters

d)

 Dropout layers

3.

When a CNN learns to detect a pattern in one location and applies it elsewhere, this is called (a)   .

4.

Adding more convolutional layers to a CNN primarily helps the network:

a)

Detect low-level abstract features

b)

Detect higher-level abstract features

c)

 Eliminate pooling layers

d)

Replace the need for normalization

5.

Why is zero-padding used in CNNs?

a)

To decrease memory usage

b)

 To increase the depth of the network

c)

 To preserve the spatial dimensions after convolution

d)

To reduce overfitting

6.

The (a)   determines how far the filter moves across the input each step.

7.

The recommended scaling for pixel values in grayscale images is:

a)

-1 to 1

b)

1 to 255

c)

0 to 100

d)

0 to 1

8.

Which of the following statements is NOT TRUE about weight sharing in CNNs?

a)

Each neuron has unique weights

b)

Filters share the same weights across spatial positions

c)

Weights are only shared between different models

d)

It increases the total number of parameters

9.

The main advantage of using convolutional layers is reduced (a)   compared to fully connected layers.

10.

The first layer of a CNN usually detects:

a)

Very abstract features

b)

Low-level features such as edges and corners

c)

Complex feature maps

d)

Fully connected vectors