Classic CNN Architectures Flashcards

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

Answer: Training on GPUs with ReLU activations and dropout

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

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

Answer: 13

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

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

Answer: Inception module

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

In ResNet, what problem do skip connections primarily solve?

Answer: Vanishing and exploding gradients in very deep networks

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

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

Answer: ResNet

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

What filter size does VGGNet use exclusively in its convolutional layers?

Answer: 3x3

VGGNet uses only 3x3 convolutional filters, showing that stacking small filters achieves the same receptive field as larger filters with fewer parameters.

What is the depth of the winning ResNet model in the ILSVRC 2015 competition?

Answer: 152 layers

The ILSVRC 2015 winning ResNet used 152 layers, achieving a top-5 error rate of 3.57%.