CE469 - Introduction to

Machine Learning
Lecturer: Asst. Prof. Ekrem BAŞER
Contact:ekrembaser@duzce.edu.tr
Presentation Files
• The presentation files used in the class are uploaded to the my
academic web page.
http://akademik.duzce.edu.tr/ekrembaser
What you need to do?
• You need to follow the lecture for understanding the concepts and
implementations.
• You need to implement the codes ownself at home.
• You need to understand the theory behind the codes for passing this
lecture.
Grades
• Mid-term exam 30%
• Homework Assignment 20%
• Final exam 50%
What is the Machine Learning?
• Machine learning (ML) is a type of artificial intelligence (AI) focused
on building computer systems that learn from data. It is a type of AI
that teaches machines how to learn, interpret and predict results
based on a set of data.
• As the world — and internet — have grown exponentially in the past
few years, machine learning processes have become common for
organizations of all kinds. For example, companies in the healthcare
sector use ML to detect and treat diseases better, while in the farming
sector machine learning helps predict harvest yields.
What is the Machine Learning?
• 4564564646652313 * 54646512312331321

• There are certain tasks where computers are really better than
humans. For example; if I ask you to multiply these two big numbers
you will take lot of time, whereas computers can do it in less than a
second.
What is the Machine Learning?
• Humans can learn everything from experiences.
• Machines can also learn from past data with the help of machine
learning.
• Machine learning algorithms create a mathematical model that,
without being explicitly programmed, aids in making predictions or
decisions with the assistance of sample historical data, or training
data. For the purpose of developing predictive models, machine
learning brings together statistics and computer science. Algorithms
that learn from historical data are either constructed or utilized in
machine learning. The performance will rise in proportion to the
quantity of information we provide.
What is the Machine Learning?

• Similarly if I ask you to search through millions of records then that

search operation is extremely difficult for humans whereas machines
can do it in a matter of nano seconds.
• Machine learning tries to make computers better at things where
traditionally humans were outperforming machines.
The Difference Between AI and ML
• AI is a science of getting machines to accomplish tasks that typically
require human level intelligence.
• Many different techniques have been proposed for AI but the most
successful and popular approach is machine learning.
• Like other AI techniques ml uses specialized algorithms to make
decisions by learning from data. Machine learning is really a subset of
AI.
• Deep learning which is a subset of ML that relies
on neural networks to learn from data.
Why study ML?
• ML is a hot topic because it's solving complex real-world problems in
so many areas. Finance, earth science, space exploration, cognitive
science and many more.
• Fields have adopted ML to solve problems specific to their domains.
• You can use ML;
• to predict the likelihood of disease from a patient's medical history
• to anticipate weather events
• to understand the sentiment of a text and to detect fake news and stop the
spread of propaganda.
Machine Learning in Real Life
• Machine learning has a big implication on our real life. One of the
important features in any email account is spam filter if you are using
Google or Yahoo or any other email account
• You will see that they filter the spam emails automatically. The way
they do it is they have seen a lot of spam emails in the past and they
train machines to learn from the content of those emails and they
filter it out for future.
Machine Learning in Real Life
• Personal assistant type of devices such as Amazon Alexa and Google
home is another example. They are getting increasingly better at
human conversation when you talk to them. They learn your lesson.
They learn your terminology and then in the future they give you an
accurate reply for the question that you asked them.
Machine Learning in Real Life
• Youtube's recommended video is another example of machine
learning where they look at your past pattern on. What kind of
content you're watching and based on that they will generate the
suggestions.
• You use machine learning every day when you run a search engine
query.
Machine Learning in Real Life
• Companies like Tesla, Google, Uber they're investing heavily in
driverless cars and all of them are using machine learning and
artificial intelligence techniques are to make car smarter.
How does Machine Learning work?
• A machine learning system builds prediction models, learns from
previous data, and predicts the output of new data whenever it
receives it. The amount of data helps to build a better model that
accurately predicts the output, which in turn affects the accuracy of
the predicted output.
How does Machine Learning work?
• For example, we have a complex problem in which we need to make
predictions. Instead of writing code, we just need to feed the data to
generic algorithms, which build the logic based on the data and
predict the output. Our perspective on the issue has changed as a
result of machine learning.
Features of Machine Learning
• Machine learning uses data to detect various patterns in a given
dataset.
• It can learn from past data and improve automatically.
• It is a data-driven technology.
• Machine learning is much similar to data mining as it also deals with
the huge amount of the data.
The importance of Machine Learning
• Rapid increment in the production of data
• Solving complex problems, which are difficult for a human
• Decision making in various sector including finance
• Finding hidden patterns and extracting useful information from data.
History of Machine Learning
Classification of Machine Learning
Supervised Learning
• The most common approach to machine learning is supervised
learning.
• In supervised learning, sample labeled data are provided to the
machine learning system for training, and the system then predicts
the output based on the training data.
• The system uses labeled data to build a model that understands the
datasets and learns about each one. After the training and processing
are done, we test the model with sample data to see if it can
accurately predict the output.
Supervised Learning
• The main objective of supervised learning is to map of the input data
to the output data. Spam filtering is an example of supervised
learning.
• Supervised learning can be grouped further in two categories of
algorithms:
• Classification
• Regression
Supervised Learning
• First, we collect a dataset of labeled training examples.
• We train a model to output accurate predictions on this dataset.
• When the model sees new, similar data it will also be accurate.
Supervised Learning Example Dataset
• Consider a simple dataset for supervised learning;
• House prices.
• We know its price, neighbordood, size or etc.
• In supervised learning the inputs and outputs of dataset should be
given.
Dataset Visualization
Supervised Learning
• Many of the applications of ML use supervised learning.
• Classifying medical images.
• Object detection.
• Translating between pair of languages, etc.
Unsupervised Learning
• Unsupervised learning is a learning method in which a machine learns
without any supervision.
• The training is provided to the machine with the set of data that has not
been labeled, classified, or categorized, and the algorithm needs to act on
that data without any supervision. The goal of unsupervised learning is to
restructure the input data into new features or a group of objects with
similar patterns.
• In unsupervised learning, we don't have a predetermined result. The
machine tries to find useful insights from the huge amount of data. It can
be further classifieds into two categories of algorithms:
• Clustering
• Association
Unsupervised Learning
• The main goal of unsupervised learning is to learn something about
the structure of data.
• Clusters hidden in the dataset. There may be groups of individuals that have
similarities.
• Outlier hidden in the dataset. There may be unusual or interesting datapoints
in the dataset.
Unsupervised Learning Dataset
Reinforcement Learning
• Reinforcement learning is a feedback-based learning method, in
which a learning agent gets a reward for each right action and gets a
penalty for each wrong action. The agent learns automatically with
these feedbacks and improves its performance. In reinforcement
learning, the agent interacts with the environment and explores it.
The goal of an agent is to get the most reward points, and hence, it
improves its performance.
• The robotic dog, which automatically learns the movement of his
arms, is an example of Reinforcement learning.
Prerequisites
• Before learning machine learning, you need to have the basic
knowledge of followings so that you can easily understand the
concepts of machine learning:
• Fundamental knowledge of probability and linear algebra.
• The ability to code in any computer language, especially in Python language.
• Knowledge of Calculus, especially derivatives of single variable and
multivariate functions.
Top Open Source Libraries for ML
• Open source machine learning libraries offer collections of pre-made
models and components that developers can use to build their own
applications, instead of having to code from scratch. They are free,
flexible, and can be customized to meet specific needs.
• Some of the most popular open-source libraries for machine learning
include:
• Scikit-learn
• PyTorch
• Kaggle
• NLTK
• TensorFlow
Prerequisities
• Linear algebra
• Programming
• Probability