CNN Classic CNN Architectures 2

Question 1

What was the primary innovation of AlexNet that enabled its 2012 ImageNet victory?

Accepted Answer

Training on GPUs with ReLU activations and dropout

Answer

AlexNet used GPU training, ReLU activations (avoiding vanishing gradients), and dropout regularization to win ILSVRC 2012 by a large margin.

Question 2

How many convolutional layers does the original VGGNet (VGG-16) contain?

Accepted Answer

13

Answer

VGG-16 has 13 convolutional layers and 3 fully connected layers, totaling 16 weight layers.

Question 3

What is the key structural unit introduced by GoogLeNet (Inception v1)?

Accepted Answer

Inception module

Answer

GoogLeNet introduced the Inception module, which applies 1x1, 3x3, and 5x5 convolutions in parallel and concatenates their outputs.

Question 4

In ResNet, what problem do skip connections primarily solve?

Accepted Answer

Vanishing and exploding gradients in very deep networks

Answer

Skip connections allow gradients to flow directly through the network, mitigating vanishing/exploding gradient problems in very deep architectures.

Question 5

Which architecture first demonstrated that network depth beyond 20 layers could be effectively trained?

Accepted Answer

ResNet

Answer

ResNet (2015) successfully trained networks with 50, 101, and even 152 layers using residual connections, proving extreme depth was achievable.

CNN - Convolutional Neural Networks Practice Test