Deep Learning CNN Convolutional Neural Networks with Python - Deep Neural Network Architecture Activity

The video tutorial explains how to build a convolutional neural network model using RGB images with dimensions 224x224x3. It describes the process of adding convolutional layers followed by max pooling layers, which reduce the spatial dimensions by half and double the number of channels. This process continues until the spatial dimensions are smaller than 10. A fully connected layer with 1000 units and a softmax layer is added at the end. The tutorial concludes with a task to calculate the total number of parameters in the model.

What is the initial size of the RGB images used in the convolutional neural network model?

• 448x448x3

• 56x56x3

• 112x112x3

• 224x224x3

What happens to the spatial dimensions after each max pooling layer in the model?

• They increase by a factor of four

• They shrink by half

• They remain the same

• They double

How do the number of channels change after each pooling layer in the model?

• They double

• They remain constant

• They triple

• They decrease by half

At what spatial dimension size should the model stop adding convolutional and pooling layers?

• When dimensions are smaller than 5

• When dimensions are smaller than 20

• When dimensions are smaller than 15

• When dimensions are smaller than 10

What is the purpose of the fully connected layer added at the end of the model?

• To reduce the number of channels

• To increase the spatial dimensions

• To classify the output into categories

• To perform additional convolution operations