Data Science and Machine Learning (Theory and Projects) A to Z - Classical CNNs: VGG

The video tutorial discusses the VGG convolutional neural network, introduced in 2014, which consists of VGG blocks. Each block typically includes several convolutional layers with 3x3 filters, followed by a Max pooling layer. The VGG network architecture builds on these blocks, with variations in the number of convolutional layers per block. The original VGG network, known as VGG 11, has five blocks with a total of eight convolutional layers and three fully connected layers. The video also mentions other successful VGG models like VGG 16 and VGG 19, and highlights the influence of VGG blocks on later networks like ResNet and Inception.

What year was the VGG network originally introduced?

• 2012

• 2013

• 2014

• 2015

What is the typical size of the convolutional filter used in VGG blocks?

• 5x5

• 3x3

• 7x7

• 1x1

How does the spatial dimension change after a max pooling layer in a VGG block?

• It remains the same

• It doubles

• It triples

• It halves

How many convolutional layers are there in the original VGG network?

• 11

• 16

• 5

• 8

What is the number of channels in the first block of the VGG network?

• 32

• 64

• 128

• 256

Which of the following is a variant of the VGG network?

• VGG20

• VGG22

• VGG13

• VGG16

Which networks were influenced by the block structure introduced in VGG?

• ResNet and Inception

• AlexNet and LeNet

• DenseNet and SqueezeNet

• GoogLeNet and MobileNet