CS7643-Quiz2 Exam 2026 Questions and
Answers
Convolution Features - Correct answer-edges
colors
textures
motifs (corners, shapes)
Receptive field - Correct answer-A region of an image (image patch) from which
the node receives input. Usually denoted by a K1 x K2 matrix.
Convolution vs Cross-correlation - Correct answer-Convolution: flip the kernel
(rotate 180) and take the dot product with image patch
Cross-correlation: do not flip the kernel to take the dot product with image patch
Advantage of using image patch - Correct answer-1./ Reduces the input parameters
to
K1 x K2 + 1 (bias)
for each output node. Thus, the total number of input parameters:
©COPYRIGHT 2025, ALL RIGHTS RESERVED 1
, N x (K1 + K2 + 1)
2./ Explicitly maintains spatial information
Weight sharing - Correct answer-The weights will represent what types of features
we will extract. The weights (W) will be the same for each output node with
respect to a specific kernel, regardless of the specific image patch we are looking
at.
The total number of input parameters:
K1 x K2 + 1
Input parameters with multiple feature extractions - Correct answer-(K1 x K2 + 1)
xM
where M is the number of features
Relationship between convolution and cross-correlation - Correct answer-Duality:
If cross-correlation is the forward pass (which is the easier operation), the
convolution operation is going to be the backward pass to calculate gradients (vice
versa)
Valid convolution - Correct answer-When the kernel is fully on the image. (No
padding)
Output size of the vanilla convolution,
©COPYRIGHT 2025, ALL RIGHTS RESERVED 2
Answers
Convolution Features - Correct answer-edges
colors
textures
motifs (corners, shapes)
Receptive field - Correct answer-A region of an image (image patch) from which
the node receives input. Usually denoted by a K1 x K2 matrix.
Convolution vs Cross-correlation - Correct answer-Convolution: flip the kernel
(rotate 180) and take the dot product with image patch
Cross-correlation: do not flip the kernel to take the dot product with image patch
Advantage of using image patch - Correct answer-1./ Reduces the input parameters
to
K1 x K2 + 1 (bias)
for each output node. Thus, the total number of input parameters:
©COPYRIGHT 2025, ALL RIGHTS RESERVED 1
, N x (K1 + K2 + 1)
2./ Explicitly maintains spatial information
Weight sharing - Correct answer-The weights will represent what types of features
we will extract. The weights (W) will be the same for each output node with
respect to a specific kernel, regardless of the specific image patch we are looking
at.
The total number of input parameters:
K1 x K2 + 1
Input parameters with multiple feature extractions - Correct answer-(K1 x K2 + 1)
xM
where M is the number of features
Relationship between convolution and cross-correlation - Correct answer-Duality:
If cross-correlation is the forward pass (which is the easier operation), the
convolution operation is going to be the backward pass to calculate gradients (vice
versa)
Valid convolution - Correct answer-When the kernel is fully on the image. (No
padding)
Output size of the vanilla convolution,
©COPYRIGHT 2025, ALL RIGHTS RESERVED 2
