CS7643 – Deep Learning Quiz 2 EXAM (2026) GRADED A+
Study Guide
Description:
High-scoring (A+) study guide for CS7643 Quiz 2 (2026). Covers all key topics in deep learning,
including neural network fundamentals, gradient descent optimization, activation functions, loss
functions, and training techniques. Organized notes and step-by-step examples make complex
concepts easy to understand and review. Perfect for students preparing for upcoming quizzes or
exams.
Tags: CS7643, Deep Learning, Quiz 2, 2026, GRADED A+, Machine Learning, Neural
Networks, Study Guide, Exam Prep, College Notes
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:
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) x M
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,
given H, W, K1, K2 - CORRECT ANSWER ✔✔✔✔✔ (H - K1 + 1) x (W - K2 + 1)
How to add padding - CORRECT 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
Stride and its consequences - CORRECT 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 - CORRECT 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 - CORRECT 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. - CORRECT 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
Effect of multiple kernels (feature extraction) on parameters - CORRECT ANSWER
✔✔✔✔✔ Each kernel, each channel has its own set of weights, but each kernel has
only 1 bias term.
(K1 x K2 x Channels + 1) x M
where M is the number of kernels
What is the purpose of pooling layer? - CORRECT ANSWER ✔✔✔✔✔
Dimensionality reduction
Study Guide
Description:
High-scoring (A+) study guide for CS7643 Quiz 2 (2026). Covers all key topics in deep learning,
including neural network fundamentals, gradient descent optimization, activation functions, loss
functions, and training techniques. Organized notes and step-by-step examples make complex
concepts easy to understand and review. Perfect for students preparing for upcoming quizzes or
exams.
Tags: CS7643, Deep Learning, Quiz 2, 2026, GRADED A+, Machine Learning, Neural
Networks, Study Guide, Exam Prep, College Notes
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:
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) x M
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,
given H, W, K1, K2 - CORRECT ANSWER ✔✔✔✔✔ (H - K1 + 1) x (W - K2 + 1)
How to add padding - CORRECT 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
Stride and its consequences - CORRECT 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 - CORRECT 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 - CORRECT 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. - CORRECT 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
Effect of multiple kernels (feature extraction) on parameters - CORRECT ANSWER
✔✔✔✔✔ Each kernel, each channel has its own set of weights, but each kernel has
only 1 bias term.
(K1 x K2 x Channels + 1) x M
where M is the number of kernels
What is the purpose of pooling layer? - CORRECT ANSWER ✔✔✔✔✔
Dimensionality reduction
