Machine_Learning_for_Babies_simple_ez.pdf

Maching learning for babies

1. Machine Learning For Babies
BY:
DR.SEIF EDDINE BOUZIANE
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 2

2. TABLE OF CONTENTS
▪Introduction
▪Machine Learning Process
▪Types of Machine Learning
▪Supervised Learning
▪Unsupervised Learning
▪Applications of Machine Learning
▪Getting Started with Machine Learning
▪Practical Examples
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 3

3. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 4

4. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 5

5. Introduction
How can we define Artificial Intelligence ?
Artificial intelligence is the simulation of human intelligence processes by machines, especially
computer systems.
What is Learning ?
"Learning is any process by which a system improves performance from experience.“ Herbert
Simon.
So, what is Machine Learning ?
"A program is said to learn from experience E with respect to some class of task T and
performance measure P. If its performance at tasks in T, as measured by P, improves with
experience E, then it is machine learning.“ Tom Mitchell
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 6

6. Introduction
Traditional Programming
Machine Learning
*Learning isn’t always useful: There is no need to “learn” to calculate payroll.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 7

7. Machine Learning Process
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 8

8. Data Collection
As you know, machines initially learn from the data that you give them. It is very important to
collect reliable data so that your machine learning model can find the correct patterns. The
quality of the data that you feed to the machine will determine how accurate your model is. If
you have incorrect or outdated data, you will have wrong outcomes or predictions which are not
relevant.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 9
Data is the new Oil
Data, like oil, isn't useful in its raw state. It needs to be
refined, processed and turned into something useful.

9. Exploratory Data Analysis (EDA)
EDA is a set of statistical and visualization techniques.
Used for seeing what the data can tell us before the preprocessing and modeling:
◦Understand the data and summarize its keys properties.
◦Discover noisy data and outliers.
◦Comprehend the distribution of the data.
◦Decide which set of data cleaning techniques to be applied.
EDA is cross-classified in two ways:
◦The method is either non-graphical or graphical.
◦The method is either univariate or multivariate (usually just bivariate).
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 10

10. Exploratory Data Analysis (EDA)
Non-graphical methods: These methods involve analyzing data without visual aids such as
charts or graphs. They often include numerical summaries, statistical tests, and computational
techniques.
For example, calculating summary statistics like mean, median, standard deviation …
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 11

11. Exploratory Data Analysis (EDA)
Graphical methods: These methods involve representing data visually using charts, graphs,
plots, or maps. Graphical methods can provide intuitive insights into data patterns, relationships,
and distributions. Examples include :
◦Scatter plots
◦Histograms
◦Box plots
◦Pie charts
◦Heat maps
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 12

12. Exploratory Data Analysis (EDA)
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 13

13. Exploratory Data Analysis (EDA)
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 14

14. Exploratory Data Analysis (EDA)
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 15

15. Exploratory Data Analysis (EDA)
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 16

16. Exploratory Data Analysis (EDA)
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 17

17. Data preparation
After you have explored your data, you have to prepare and clean it. You can do this by :
▪Remove irrelevant and unwanted data
▪Deal with missing values either by removing the columns or rows, or by imputing them, i.e, filling them
using various techniques, like using the median value … etc.
▪Remove duplicate data
▪Data type conversion.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 18

18. Feature Engineering
Feature engineering is the process of transforming raw data into features that better represent
the underlying problem to the machine learning algorithms.
It is one of the most important steps in any machine learning project, as good features can lead
to significantly better model performance.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 19

19. Feature Engineering
▪Feature Creation
▪Derive new features from existing ones
▪Combine multiple features using mathematical operations
▪Dimensionality reduction techniques (PCA, t-SNE, etc.)
▪Feature Transformation
▪Scaling (normalization, standardization)
▪Encoding (one-hot, label, target encoding)
▪Mathematical transformations (log, square root, etc.)
▪Feature Extraction
▪Text feature extraction (TF-IDF, word embeddings, etc.)
▪Image feature extraction (HOG, SIFT, deep learning, etc.)
▪Feature Selection
▪Techniques like correlation analysis, recursive feature elimination, etc.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 20

20. Model Training
What is a machine learning Model?
Machine learning models are computer programs that are used to recognize patterns in data or
make predictions.
Machine learning models are created from machine learning algorithms, which undergo a
training process using either labeled, unlabeled, or mixed data. Different machine learning
algorithms are suited to different goals.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 21

21. Model Training
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 22

22. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 23

23. Unsupervised Learning
Unsupervised learning in artificial intelligence is a type of machine learning that learns from
data without human supervision. Unlike supervised learning, unsupervised machine learning
models are given unlabeled data and allowed to discover patterns and insights without any
explicit guidance or instruction.
Unsupervised learning algorithms are better suited for more complex processing tasks, such as
organizing large datasets into clusters. They are useful for identifying previously undetected
patterns in data and can help identify features useful for categorizing data.
In general, there are three types of unsupervised learning tasks: clustering, association rule
mining, and dimensionality reduction.

MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 24

24. Clustering
Clustering is a technique for exploring raw, unlabeled data and breaking it down into groups (or
clusters) based on similarities or differences. It is used in a variety of applications, including
customer segmentation, fraud detection, and image analysis. Clustering algorithms split data
into natural groups by finding similar structures or patterns in uncategorized data.
There are several types of unsupervised learning algorithms that are used for clustering , for
example:
Partitioning clustering: Construct various partitions (clusters) and Data is grouped in a way
where a single data point can only exist in one cluster. One of the most known algorithms is K-
Means.
Hierarchical clustering: Data is divided into distinct clusters based on similarities, which are then
repeatedly merged and organized based on their hierarchical relationships.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 25

25. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 26

26. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 27

27. K-Means
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 28

28. Hierarchical Clustering
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 29

29. Supervised Learning
Supervised learning is a category of machine learning that uses labeled datasets to train
algorithms to predict outcomes and recognize patterns. Unlike unsupervised learning,
supervised learning algorithms are given labeled training to learn the relationship between the
input and the outputs.
The data used in supervised learning is labeled — meaning that it contains examples of both
inputs (called features) and correct outputs (labels). The algorithms analyze a large dataset of
these training pairs to infer what a desired output value would be when asked to make a
prediction on new data.
Supervised learning in machine learning is generally divided into two categories: classification
and regression.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 30

30. Regression
Regression algorithms are used to predict a real or continuous value, where the algorithm
detects a relationship between two or more variables.
A common example of a regression task might be predicting a salary based on work experience.
For instance, a supervised learning algorithm would be fed inputs related to work experience
(e.g., length of time, the industry or field, location, etc.) and the corresponding assigned salary
amount. After the model is trained, it could be used to predict the average salary based on work
experience.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 31

31. Linear Regression
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 32

32. Classification
Classification algorithms are used to group data by predicting a categorical label or output
variable based on the input data. Classification is used when output variables are categorical,
meaning there are two or more classes.
One of the most common examples of classification algorithms in use is the spam filter in your
email inbox. Here, a supervised learning model is trained to predict whether an email is spam or
not with a dataset that contains labeled examples of both spam and legitimate emails.
The algorithm extracts information about each email, including the sender, the subject line,
body copy, and more. It then uses these features and corresponding output labels to learn
patterns and assign a score that indicates whether an email is real or spam
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 33

33. Decision Trees
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 34

34. SVM
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 35

35. Logistic Regression
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 36

36. Neural Networks
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 37

37. Applications of ML
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 38

38. Starting with ML
In 2024, the landscape of machine learning (ML) continues to evolve at a breathtaking pace,
with new tools and technologies emerging to streamline the development, deployment, and
management of ML models. The right set of tools can significantly enhance the efficiency of ML
projects, from data preprocessing and model training to evaluation and deployment.
Machine learning tools and techniques are indispensable in the modern era, in the next slide I’ll
present some of the most popular data science and ML tools that can help you Whether you're
embarking on your first ML project or looking to refine your existing workflows.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 39

39. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 40

40. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 41

41. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 42

42. Practical Example N°01
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 43

43. Practical Example N°01
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 44
Hierarchical Clustering
You are tasked with developing a recommendation system for an anime streaming application.
The goal is to group anime series based on their genres using hierarchical clustering.

44. Practical Example N°02
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 45

45. Practical Example N°02
K-Means Clustering
we shall use the Country Dataset, HELP International is an international humanitarian NGO that
is committed to fighting poverty and providing the people of backward countries with basic
amenities and relief during the time of disasters and natural calamities.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 46

46. Practical Example N°03
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 47

47. Practical Example N°03
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 48
Linear & Polynomial Regression
▪We gonna use Cab’s demand data to predict the demand on Cab’s pickups number at a specific
time of the day.
▪Secondly, we gonna use premier league dataset to make a model that is able to predict the
market value of a football player based on some features.

48. Practical Example N°04
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 49

49. Practical Example N°04
Classification.
We’re going to use a breast cancer dataset to predict whether a tumor is malignant or benign.
MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 50

50. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 51

51. MACHINE LEARNING FOR BABIES - DR. SEIF EDDINE BOUZIANE 52
By. Dr Seif Eddine Bouziane