Page 1 of 57
CS 7643 / CS7643: DEEP LEARNING QUIZ 2, 3 & 4
(LATEST 2025/ 2026 UPDATES STUDY BUNDLE
PACKAGE WITH SOLUTIONS) QUESTIONS & ANSWERS
| GRADE A | 100% CORRECT (VERIFIED SOLUTIONS) -
GEORGIA TECH
Convolution Features .....ANSWER.....edges
colors
textures
motifs (corners, shapes)
Receptive field .....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 .....ANSWER.....Convolution: flip
the kernel (rotate 180) and take the dot product with image
patch
,Page 2 of 57
Cross-correlation: do not flip the kernel to take the dot product
with image patch
Advantage of using image patch .....ANSWER.....1./ Reduces the
input parameters to
K1 x K2 + 1 (bias)
for each output node. Thus, the total number of input parameters:
N x (K1 + K2 + 1)
2./ Explicitly maintains spatial information
Weight sharing .....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
,Page 3 of 57
Input parameters with multiple feature extractions
.....ANSWER.....(K1 x K2 + 1) x M
where M is the number of features
Relationship between convolution and cross-correlation
.....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 .....ANSWER.....When the kernel is fully on the
image. (No padding)
Output size of the vanilla convolution,
given H, W, K1, K2 .....ANSWER.....(H - K1 + 1) x (W - K2 + 1)
How to add padding .....ANSWER.....Increases the size of the
image with P in both directions (top & bottom, left & right)
--> (H + 2P) x (W + 2P)
Can be filled with zeros or mirror the image
, Page 4 of 57
Stride and its consequences .....ANSWER.....Number of pixels
moving forward when parsing the patch through images.
Loss of information
Used for dimensionality reduction
Effect of channels on output size .....ANSWER.....It doesn't have
effect on the output size: we perform the dot product for each
channels and summing them up.
Effect of channels on parameters .....ANSWER.....Each channel
might have its own weights with respect to the same kernel.
M x (Ch x K1 x K2 + 1)
Effect of multiple kernels (feature extraction) on output size.
.....ANSWER.....The kernel size should be equal (K1 x K2) for
each kernel within the layer. The output size:
(H - K1 + 1) x (W - K2 + 1) x Number of Kernels
CS 7643 / CS7643: DEEP LEARNING QUIZ 2, 3 & 4
(LATEST 2025/ 2026 UPDATES STUDY BUNDLE
PACKAGE WITH SOLUTIONS) QUESTIONS & ANSWERS
| GRADE A | 100% CORRECT (VERIFIED SOLUTIONS) -
GEORGIA TECH
Convolution Features .....ANSWER.....edges
colors
textures
motifs (corners, shapes)
Receptive field .....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 .....ANSWER.....Convolution: flip
the kernel (rotate 180) and take the dot product with image
patch
,Page 2 of 57
Cross-correlation: do not flip the kernel to take the dot product
with image patch
Advantage of using image patch .....ANSWER.....1./ Reduces the
input parameters to
K1 x K2 + 1 (bias)
for each output node. Thus, the total number of input parameters:
N x (K1 + K2 + 1)
2./ Explicitly maintains spatial information
Weight sharing .....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
,Page 3 of 57
Input parameters with multiple feature extractions
.....ANSWER.....(K1 x K2 + 1) x M
where M is the number of features
Relationship between convolution and cross-correlation
.....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 .....ANSWER.....When the kernel is fully on the
image. (No padding)
Output size of the vanilla convolution,
given H, W, K1, K2 .....ANSWER.....(H - K1 + 1) x (W - K2 + 1)
How to add padding .....ANSWER.....Increases the size of the
image with P in both directions (top & bottom, left & right)
--> (H + 2P) x (W + 2P)
Can be filled with zeros or mirror the image
, Page 4 of 57
Stride and its consequences .....ANSWER.....Number of pixels
moving forward when parsing the patch through images.
Loss of information
Used for dimensionality reduction
Effect of channels on output size .....ANSWER.....It doesn't have
effect on the output size: we perform the dot product for each
channels and summing them up.
Effect of channels on parameters .....ANSWER.....Each channel
might have its own weights with respect to the same kernel.
M x (Ch x K1 x K2 + 1)
Effect of multiple kernels (feature extraction) on output size.
.....ANSWER.....The kernel size should be equal (K1 x K2) for
each kernel within the layer. The output size:
(H - K1 + 1) x (W - K2 + 1) x Number of Kernels
