CNN Pooling and Activation Functions 2

Question 1

What is the primary effect of average pooling compared to max pooling in CNNs?

Accepted Answer

Smooths feature maps by computing the mean of values in each region

Answer

Average pooling computes the mean of all values in a pooling window, resulting in smoother feature maps compared to max pooling.

Question 2

Which activation function is most commonly used in the hidden layers of modern deep CNNs?

Accepted Answer

ReLU

Answer

ReLU (Rectified Linear Unit) is the dominant activation in hidden layers because it is computationally efficient and mitigates the vanishing gradient problem.

Question 3

Global Average Pooling (GAP) is frequently used at the end of a CNN to replace which traditional layer?

Accepted Answer

Fully connected (dense) layer

Answer

GAP reduces each feature map to a single value, replacing large fully connected layers and dramatically reducing parameter count.

Question 4

What is the 'dying ReLU' problem?

Accepted Answer

Neurons with ReLU permanently output zero because their weights push inputs negative

Answer

When neurons receive consistently negative inputs, ReLU outputs zero with zero gradient, so weights never update—the neuron effectively 'dies.'

Question 5

In a CNN, a 4×4 feature map with a 2×2 max pooling kernel and stride 2 produces an output of what size?

Accepted Answer

2×2

Answer

With a 2×2 kernel and stride 2, each dimension is halved: (4-2)/2 + 1 = 2, so the output is 2×2.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Pooling and Activation Functions 2