Scribd
Upload
32 views3 pages

Exercise #2

The document contains multiple-choice questions and exercises related to deep learning concepts, including stages of deep learning, model evaluation metrics, and the development of deep learning models. It also includes true/false statements and definitions related to supervised and unsupervised learning, as well as practical tasks such as calculating accuracy and designing neural networks. Overall, it serves as a comprehensive review of key deep learning principles and practices.

Uploaded by

Yousef
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
32 views3 pages

Exercise #2

The document contains multiple-choice questions and exercises related to deep learning concepts, including stages of deep learning, model evaluation metrics, and the development of deep learning models. It also includes true/false statements and definitions related to supervised and unsupervised learning, as well as practical tasks such as calculating accuracy and designing neural networks. Overall, it serves as a comprehensive review of key deep learning principles and practices.

Uploaded by

Yousef
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

[1] i) MCQ

1- Deep learning (DL) is divided into three different evolutionary stages:


a) Supervised - Unsupervised – Semisupervised b) Representation– Evaluation– Optimization
c) Artificial narrow intelligence – Artificial general intelligence – Artificial superintelligence
d) Feature extraction – Dimensionality reduction – Complexity
2- The three most important components of every deep learning (DL) algorithm are:
a) Overfitting – understanding – computation speed b) Representation– Evaluation– Optimization
c) Feature extraction – Dimensionality reduction – Complexity d) All the previous
3- Factors to consider for improving DL models are:
a) the use of proper model architecture along with large enough data.
b) the quality, quantity, and relevance of the data you feed into it
c) training time, test time, accuracy, and size. d) a and b
4- Which of the following metrics are used to evaluate classification models?
a) Area under the ROC curve b) F1 score c) Confusion matrix d) All the before
5- Which of the following metrics are used to evaluate regression models?
a) Mean Squared Error (MSE) b) Accuracy c) Recall d) All the before
ii) Show an example to illustrate the common terms to describe the data. What is the difference between labeled
and unlabeled data?
iii) State the steps involved in developing a DL model. Mention five types of DL tasks.

[2] i) What success and error rates are based on the


given confusion matrix in a multi-class prediction
problem? Does this give us a good metric?
ii) Compute the accuracy, precision, recall, and F1
score.
iii) Draw a schematic diagram for a DL model to
find a compromise between its complexity and
prediction accuracy.

[3] i) Fill in the spaces with suitable numbers:


1- An input image 32x32 of a traffic sign is filtered by 4 (5×5) convolutional kernels, creating…… feature maps.
2- These feature maps are subsampled by max-pooling 4 (2x2) which gives ……. feature maps.
3- The next layer applies 10 (5×5) convolutional kernels to these subsampled images, which give …… feature
maps, and again, we pool the feature maps by 10 (2x2) subsampling, creating…….
ii) What is the total number of parameters in part (i)?
iii) Explain a definition for each of the variables in the
simple neuron (perceptron) mathematical representation
shown in the figure:

[4]
i) True/False
1- Regression analysis is a subcategory of supervised learning that aims to predict a categorical class label of a
new instance.
2- Classification is a method used to predict continuous target variables, which represent numerical values.
3- Data cleaning is the process of manipulating the data to make it usable for analysis, while data wrangling is
the process of making sure that the data is accurate and consistent.

1
4- Data scaling is the process of ensuring that all features contribute equally to the model and avoid the domination
of features with larger values.
5- Due to imbalanced data, most DL algorithms are unable to predict the minority class's data properly.
6- F1 score = 1⁄(1 + (𝐹𝑛 + 𝐹𝑝 )⁄2𝑇𝑝 ) ranges between 0 and 1.
ii) In the context of DL, choose from set B the definition that matches the expression in A.
A B
1- The philosophy of DL (DL) is a program generated by an algorithm without being
explicitly programmed by any human being.
2. A deep learning (DL) model is refers to a set of training examples where the labels are
already known.
3. Overfitting occurs associated tags or labels representing the outcome or
category of the data.
4. Deep Learning (DL) is built on the rules of inferences, heuristics, discovery,
reasoning, induction, and guesswork.
5. Supervised learning is represented as a vector 𝒙∈ ℝ𝒏 where each entry 𝒙𝒊 of
the vector is another feature.
6. Unsupervised learning rescaling features to the range of [0, 1]
7. Labeled data comes with is to reduce the effect of overfitting
8. A dataset example or sample when a model learns to perform well on the training data
but does not generalize well to unseen data.
9. Normalization refers to multi-neural network architecture statistical tool to
explore and analyze the data.
10. Advantage of using CNN over (MLP) is based on finding meaningful patterns and groups in
the unlabeled data based on features and purposes.
iii) Using the idea of a fully functioning feedforward network shows how to design a simple task: learning the
XOR function. Draw the implementation network.

Sample solutions:
Solution of Q2
[2] i)

Error = (Fp + Fn)/ (total data set) = (10 + 2 + 14 + 18)/ 200 = 0.22 = 22%
Success = 1 – error = 1 – 0.22 = 0.78 = 78%

ii)
Accuracy = (88+40+12)/200 = 0.7 = 70%, Precision = 0.58 = 58%, Recall = 0.62 = 62%, F1 Score = 0.63 = 63%

2
iii)

odel raining uning and valuation


Attem t to find a ood com romise bet een the com lexity of a model and its
rediction accuracy on the trainin data
se three sets (trainin validation and test data) to build tune and measure the
erformance of a model

You might also like