Convolutional Layer Operations Flashcards

What happens to spatial dimensions when a 5×5 filter is applied with stride=2 and no padding to a 32×32 input?

Answer: 14×14

Output size = floor((32 - 5) / 2) + 1 = floor(13.5) + 1 = 14, giving 14×14.

In a convolutional layer, what does 'same' padding ensure?

Answer: Output spatial size equals input spatial size

'Same' padding adds zeros around the input so the output height and width match the input when stride=1.

Which operation sums element-wise products between a filter and a receptive field in a CNN?

Answer: Cross-correlation

Cross-correlation (often loosely called convolution in deep learning) computes the sum of element-wise products without flipping the filter.

A convolutional layer has 64 filters of size 3×3 applied to a 3-channel input. How many learnable parameters does it have (excluding bias)?

Answer: 1728

Parameters = filters × kernel_h × kernel_w × input_channels = 64 × 3 × 3 × 3 = 1728.

What is the primary purpose of using multiple filters in a single convolutional layer?

Answer: To detect multiple distinct features simultaneously

Each filter learns to detect a different feature (e.g., edge, texture), producing one feature map per filter.

When stride > 1 is used in a convolutional layer, what is the primary effect?

Answer: Spatial downsampling of the feature map

A larger stride causes the filter to skip positions, reducing the output spatial dimensions (downsampling).

Which quantity represents the number of output feature maps produced by a convolutional layer?

Answer: Number of filters

Each filter produces exactly one output feature map, so the number of output channels equals the number of filters.