CNN Classic CNN Architectures 3

Question 1

How does GoogLeNet reduce computational cost before applying 3x3 and 5x5 convolutions in the Inception module?

Accepted Answer

By applying 1x1 convolutions as bottlenecks

Answer

1x1 convolutions act as bottlenecks that reduce the number of input channels before more expensive 3x3 and 5x5 convolutions are applied.

Question 2

LeNet-5, designed for handwritten digit recognition, was trained on which dataset?

Accepted Answer

MNIST

Answer

LeNet-5 was developed by LeCun et al. to classify handwritten digits from the MNIST dataset, achieving state-of-the-art performance in the 1990s.

Question 3

Which activation function did AlexNet popularize as an alternative to sigmoid and tanh?

Accepted Answer

ReLU

Answer

AlexNet popularized ReLU (Rectified Linear Unit), which trains faster than sigmoid/tanh and mitigates the vanishing gradient problem.

Question 4

What is the total number of layers (depth) in the original GoogLeNet (Inception v1)?

Accepted Answer

22

Answer

GoogLeNet is 22 layers deep (27 including pooling layers), which was very deep for its time when it won ILSVRC 2014.

Question 5

What regularization technique unique to AlexNet was placed after the first two fully connected layers?

Accepted Answer

Dropout with 0.5 probability

Answer

AlexNet applied dropout with p=0.5 after the first two fully connected layers, randomly zeroing activations during training to prevent co-adaptation.

CNN - Convolutional Neural Networks Practice Test