Introduction to

Machine Learning
Chapter 1 - Introduction

by Mintesinot Getachew (MSc.)

 ❑ What is machine learning?

Outline
❑ History and relationships to other fields
❑ Essential math and statistics for
machine learning
❑ Applications of machine learning
❑ Types of machine learning techniques

2
 Introduction
❑ Machine Learning is branch of AI that focuses on using data and algorithms to
mimic human learning, allowing machines to improve over time, becoming
increasingly accurate when making predictions or classifications, or
uncovering data-driven insights.
❑ In recent years, the use of machine learning technologies has become
ubiquitous in everyday life.
❑ It is a research field at the intersection of statistics, artificial intelligence, and
computer science and is also known as predictive analytics or statistical
learning. T

3
Did you know?
Arthur Samuel created the term "machine learning" in reference to his
research in the early 1960s. That research was based on the checkers
game that Robert Nealy played against an IBM 7094 computer and lost.
Although this is minor compared to what machines can do today, it
was a groundbreaking milestone at the time.

4
 Why Machine Learning?
• Scalability: Early intelligent applications used handcoded rules of "if" and "else" decisions.
These systems are often limited in their ability to handle large and complex datasets. ML
algorithms can handle vast amounts of data and can scale to meet the needs of modern
applications.
• Flexibility: Rule-based systems are often rigid and inflexible, requiring manual intervention
to update the rules. In contrast, ML models can adapt and learn from new data, allowing
them to improve over time and handle a wider range of tasks.
• Automation: Rule-based systems often require significant manual effort to create and
maintain the rules. In contrast, ML models can be trained using data, which reduces the
need for manual intervention.
• Improved accuracy: ML algorithms can often achieve higher accuracy than rule-based
systems, particularly when dealing with complex data such as images or natural language.
5
 Why Machine Learning?
Think of a spam filter, whose job is to move the appropriate incoming email messages
to a spam folder. You could make up a blacklist of words that would result in an email
being marked as spam. This would be an example of using an expert-designed rule-
based system to design an “intelligent” application. Manually crafting decision rules is
feasible for some applications, particularly those in which humans have a good
understanding of the process to model.
However, using handcoded rules to make decisions has two major disadvantages:
• The logic required to make a decision is specific to a single domain and task.
Changing the task even slightly might require a rewrite of the whole system.
• Designing rules requires a deep understanding of how a decision should be made by
a human expert.
6
Applications of ML

7
 Applications of ML …Cont’d

Image Recognition
• Image recognition is one of the most common applications of machine learning.
It is used to identify objects, persons, places, digital images, etc.
• One of the popular use case of image recognition and face detection is,
Automatic friend tagging suggestion:
• Facebook provides us a feature of auto friend tagging suggestion. Whenever we
upload a photo with our Facebook friends, then we automatically get a tagging
suggestion with name, and the technology behind this is machine learning's face
detection and recognition algorithm.

8
 Applications of ML …Cont’d

Speech Recognition
• While using Google, we get an option of "Search by voice," it comes under
speech recognition, and it's a popular application of machine learning.
• Speech recognition is a process of converting voice instructions into text, and it
is also known as "Speech to text", or "Computer speech recognition."
• At present, machine learning algorithms are widely used by various applications
of speech recognition. Google assistant, Siri, Cortana, and Alexa are using
speech recognition technology to follow the voice instructions.

9
 Applications of ML …Cont’d
Product Recommendation
• Machine learning is widely used by various e-commerce and entertainment
companies such as Amazon, Netflix, etc., for product recommendation to the
user.
• Whenever we search for some product on Amazon, then we started getting an
advertisement for the same product while internet surfing on the same browser
and this is because of machine learning.
• Google understands the user interest using various machine learning algorithms
and suggests the product as per customer interest.
• As similar, when we use Netflix, we find some recommendations for
entertainment series, movies, etc., and this is also done with the help of
machine learning. 10
 Applications of ML …Cont’d

Self-driving cars
• One of the most exciting applications of machine learning is self-driving
cars.
• Tesla, the most popular car manufacturing company is working on self-
driving car. It is using unsupervised learning method to train the car
models to detect people and objects while driving.

11
 Applications of ML …Cont’d

Email Spam and Malware Filtering

• Whenever we receive a new email, it is filtered automatically as
important, normal, and spam.
• We always receive an important mail in our inbox with the important
symbol and spam emails in our spam box, and the technology behind
this is Machine learning.

12
 Applications of ML …Cont’d

Virtual Personal Assistant

• Virtual personal assistants such as Google assistant, Alexa, Cortana, Siri
help us in finding the information using our voice instruction.
• These assistants can help us in various ways just by our voice
instructions such as Play music, call someone, Open an email,
Scheduling an appointment, etc.
• These virtual assistants use machine learning algorithms as an important part.

13
 Applications of ML …Cont’d

Stock Market trading

• Machine learning is widely used in stock market trading.
• In the stock market, there is always a risk of up and downs in shares, so
for this machine learning's long short term memory neural network can
be used for the prediction of stock market trends.

14
 Machine learning Life cycle

• Machine learning has given the computer systems the abilities to

automatically learn without being explicitly programmed.
• Machine learning life cycle is a cyclic process to build an efficient
machine learning solution.
• The main purpose of the life cycle is to find a solution to the problem or
project.

15
 1 2 3
Data Gathering Data Preparation
4
Data Wrangling Data Analysing

7 6 5
Deployment Test Model Train Model

Machine Learning life cycle

 Types of Machine Learning

• Machine learning involves showing a large volume of data to a machine

so that it can learn and make predictions, find patterns, or classify data.
The three machine learning types are:
1. Supervised
2. Unsupervised
3. Reinforcement learning.

17
 Supervised learning
• This machine learning type got its name because the machine is
“supervised” while it's learning, which means that you’re feeding the
algorithm information to help it learn.
• Supervised Learning is defined as the category of data analysis where
the target outcome is known or labeled e.g. whether the customer(s)
purchased a product, or did not.
• Supervised learning relies on labeled data to train algorithms.
• Common algorithms used during supervised learning include neural
networks, decision trees, linear regression, and support vector
machines. 18
 Supervised learning …Cont’d

Use case example

For example, if you were trying to learn about the relationships between
loan defaults and borrower information, you might provide the machine
with 500 cases of customers who defaulted on their loans and another
500 who didn't. The labeled data “supervises” the machine to figure out
the information you're looking for.

19
 Supervised learning …Cont’d

Supervised learning is effective for a variety of business purposes,

including sales forecasting, inventory optimization, and fraud detection.
Some examples of use cases include:
• Predicting real estate prices
• Classifying whether bank transactions are fraudulent or not
• Finding disease risk factors
• Determining whether loan applicants are low-risk or high-risk
• Predicting the failure of industrial equipment's mechanical parts

20
 Unsupervised learning
• Unsupervised learning is a learning method in which a machine learns
without any supervision.
• Unsupervised learning doesn't use labeled training sets and data,
Instead, the machine looks for patterns in the data.
• This machine learning type is very helpful when you need to identify
patterns and use data to make decisions.
• Common algorithms used in unsupervised learning include Hidden
Markov models, k-means, hierarchical clustering, and Gaussian mixture
models.
21
 Unsupervised learning …Cont’d

• Common algorithms used in unsupervised learning include Hidden

Markov models, k-means, hierarchical clustering, and Gaussian mixture
models.
Use case example
• Using the example from supervised learning, let's say you didn't know
which customers did or didn't default on loans. Instead, you'd provide
the machine with borrower information and it would look for patterns
between borrowers before grouping them into several clusters.

22
 Unsupervised learning …Cont’d

A few example use cases include:

• Creating customer groups based on purchase behavior
• Grouping inventory according to sales and/or manufacturing metrics
• Pinpointing associations in customer data (for example, customers who
buy a specific style of handbag might be interested in a specific style of
shoe)

23
 Reinforcement learning

• Reinforcement learning is the closest machine learning type to how

humans learn.
• Feedback-based learning method.
• Learning agent gets a positive reward for each right action and gets a
negative reward for each wrong action.
• Common algorithms include temporal difference, deep adversarial
networks, and Q-learning.

24
 Reinforcement learning …Cont’d

Use case example

• Going back to the bank loan customer example, you might use a
reinforcement learning algorithm to look at customer information. If the
algorithm classifies them as high-risk and they default, the algorithm
gets a positive reward. If they don't default, the algorithm gets a
negative reward. In the end, both instances help the machine learn by
understanding both the problem and environment better.

25
 Reinforcement learning …Cont’d

Some examples of uses include

• Teaching cars to park themselves and drive autonomously
• Dynamically controlling traffic lights to reduce traffic jams
• Training robots to learn policies using raw video images as input that
they can use to replicate the actions they see

26
Introduction to AI
"Artificial intelligence is the future and the future
is here.” Dave Waters

27