Scribd
Upload
9 views

Exercise #1

The document outlines a series of exercises related to deep learning, including drawing a workflow diagram and categorizing deep learning techniques. It also involves applying convolution operations to an image, computing feature maps through various layers, and determining the total number of parameters in a given problem. Additionally, it addresses how to verify model performance regarding underfitting and overfitting.

Uploaded by

Yousef
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
9 views

Exercise #1

The document outlines a series of exercises related to deep learning, including drawing a workflow diagram and categorizing deep learning techniques. It also involves applying convolution operations to an image, computing feature maps through various layers, and determining the total number of parameters in a given problem. Additionally, it addresses how to verify model performance regarding underfitting and overfitting.

Uploaded by

Yousef
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Exercise #1

[1] Draw a diagram to show the stages of a deep learning workflow to solve real-world
problems.
[2] Show a schematic to present the taxonomy of the Deep Learning techniques into major
applied categories.

[3] Convolution between a kernel k of odd size n and an image f is defined by the formula:
𝑛2 𝑛2

𝑔(𝑥. 𝑦) = ∑ ∑ 𝑘(𝑛2 + 𝑖, 𝑛2 + 𝑗)𝑓(𝑥 − 𝑖, 𝑦 − 𝑗)


𝑖=−𝑛2 𝑗=−𝑛2
𝑛
Where 𝑛2 = ⌊ ⌋, floor function.
2
i- Write the pseudocode for applying the convolution kernel to an image as stated above.
−3 3 3 2 1 4 −1
ii- Let 𝑘 = [ 3 −3 3 ] , 𝑓 = [0 3 1 1]
2 1 −1 2
3 3 −3
1 3 −4 2
Compute the convolution 𝐶 = 𝑘 ∗ 𝑓
[4] Fill in the spaces with suitable numbers:
1- 3 5×5 convolutional kernels filter an input image 255x255 of a traffic sign at stride 2,
which creates…… feature maps.
2- These feature maps are subsampled by max-pooling 3 (2x2), which gives …….. feature
maps.
3- The next layer applies 10 (7×7) convolutional kernels at stride 3 to these subsampled
images, which give…… feature maps, and again we pool the feature maps by 10 (2x2)
subsampling.
4- The next layer applies 6 (9×9) convolutional kernels at stride 4 to these subsampled
images, which give…… feature maps, and again we pool the feature maps by 6 (2x2)
subsampling.
[5] What is the total number of parameters in the problem [4]?
[6] How do you verify that the model in problem [4] has no underfitting or overfitting?

You might also like