CNN Pooling and Activation Functions 4

Question 1

In Parametric ReLU (PReLU), what is learned during training?

Accepted Answer

The slope of the activation for negative inputs, as a trainable parameter

Answer

PReLU learns the negative-slope coefficient α via backpropagation, allowing the network to adapt the activation shape rather than fixing it at a preset value.

Question 2

Which pooling variant performs a weighted average where closer elements contribute more, based on their distance from the pooling region center?

Accepted Answer

Weighted average pooling

Answer

Weighted average pooling assigns higher weights to elements nearer the center of the pooling window, emphasizing spatially central activations.

Question 3

What is the key computational advantage of max pooling over learned downsampling (e.g., strided convolutions)?

Accepted Answer

Max pooling has no trainable parameters, reducing model complexity and memory

Answer

Max pooling is a fixed operation with no learnable parameters, making it cheaper in memory and compute compared to strided convolutions that add weights.

Question 4

SELU (Scaled Exponential Linear Unit) activation is designed to achieve what property automatically?

Accepted Answer

Self-normalizing activations: mean near zero, variance near one across layers

Answer

SELU with its specific scale and slope parameters causes activations to converge toward zero mean and unit variance during forward propagation, enabling deep networks without batch norm.

Question 5

Spatial Pyramid Pooling (SPP) enables CNNs to accept inputs of varying sizes primarily by doing what?

Accepted Answer

Applying pooling at multiple scales and concatenating outputs into a fixed-length vector

Answer

SPP pools the final feature maps at several granularities (e.g., 1×1, 2×2, 4×4) and concatenates the results, always producing a fixed-size representation regardless of input size.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Pooling and Activation Functions 4