MACHINE LEARNING (UE22CS352A)
Introduction to Machine Learning
Course Instructor: Dr Pooja Agarwal
Professor, Dept. of CSE
MACHINE LEARNING
Introduction to Machine Learning
The slides are generated from various internet resources and books,
with valuable contributions from multiple professors and teaching
assistants in the university.
MACHINE LEARNING
Machine Learning UE22CS352A : Course Content
MACHINE LEARNING
Machine Learning UE22CS352A : Course Content
MACHINE LEARNING
Machine Learning UE22CS352A : Books
Reference Books:-
1:“Machine Learning”, Tom Mitchell, McGraw Hill Education
(India),2013.
2: “Machine Learning: The Art and Science of Algorithms that
Make Sense of Data”, Peter Flach, Cambridge University Press
(2012).
3: “Generative Deep Learning, David Foster, O‟reilly media,
2nd Edition, 2023, ISBN : 9781098134181.
4: “Attention is all you need “, Vaswani Ashish, Shazeer
Noam, Parmar Niki, Uszkoreit Jakob, Jones Llion, Gomez
Aidan N., Kaiser Łukasz, and Polosukhin Illia. 2017, In
Advances in Neural Information Processing Systems. 5998–
6008
MACHINE LEARNING
Machine Learning UE22CS352A : Lab Sessions
MACHINE LEARNING
INTRODUCTION
Source : https://www.javatpoint.com/machine-learning
MACHINE LEARNING
INTRODUCTION
What is a Machine ?
• In the context of Machine Learning, a machine refers to a
computing system that is capable of learning and improving its
performance on a specific task without being explicitly
programmed.
• These machines are designed to process large amounts of
data, extract patterns, and make predictions or decisions based
on the learned information.
• The term "machine" in this context typically refers to a
computer or computational device equipped with algorithms
Digital Computer Processing System
and models that enable it to perform learning tasks
autonomously.
MACHINE LEARNING
INTRODUCTION
Why Learn?
Machine learning is programming computers to optimize a
performance criterion using example data or past experience.
Learning is used when:
➢ Human expertise does not exist (navigating on Mars),
➢ Humans are unable to explain their expertise (speech
recognition)
➢ Solution changes in time (routing on a computer network)
➢ Solution needs to be adapted to particular cases (user
biometrics)
➢ Learning general models from a data of particular examples
➢ Data is cheap and abundant (data warehouses, data marts);
knowledge is expensive and scarce.
➢ Build a model that is a good and useful approximation to the
data.
MACHINE LEARNING
What is Machine Learning
Machine learning (ML) is a subset of artificial intelligence (AI) that focuses on the
development of algorithms and statistical models that enable computers to learn
from and make predictions or decisions based on data.
MACHINE LEARNING
Applications of Machine Learning
Healthcare: Diagnosing diseases, personalized medicine,
predicting patient outcomes.
Finance: Fraud detection, algorithmic trading, credit
scoring.
Retail: Personalized recommendations, inventory
management, demand forecasting.
Transportation: Autonomous vehicles, traffic prediction,
route optimization.
Natural Language Processing (NLP): Language translation,
sentiment analysis, chatbots.
MACHINE LEARNING
Artificial Intelligence and Machine Learning
Machine Intelligence
Machine learning is defined as systems that enable
a computer system to learn from inputs.
Artificial intelligence is composed of systems that allow
computers to imitate human cognitive processes
Artificial Machine
Intelligence Learning
The mental action or process of acquiring knowledge and
understanding through thought, experience, and the senses.
MACHINE LEARNING
Examples of Machine Intelligence
Source: https://giphy.com/search/artificial-intelligence
MACHINE LEARNING
Artificial Intelligence Vs. Human Intelligence
Source:https://techswizard.com/gadget/artificial-intelligence-vs-human-intelligence/
MACHINE LEARNING
Human Intelligence
Identify Remember
Patterns in what
Communicate
data people have
with people
said
Use available
information to
Adapt to
take decisions
new
situations
MACHINE LEARNING
Artificial Intelligence
MACHINE LEARNING
An Intuitive Definition
• Consider the world ,we have humans and we have computers
• Can we get computers to learn from experience too???
• YES -and that is precisely what machine learning means
• but for computers we have a different term for experience that is data
data
Learn from experience
Learn from experience Follow instructions
MACHINE LEARNING
Learning from Data
• Let us see one example to understand how a machine learns from experience(data)
• Consider we have two house with following price and we need to predict the price of the medium
sized house
• We will plot them on a graph with some other data ,find a best fit line to predict its price
• This method is called linear regression ,how to find the best fit line ? we will see it in further session.
30L 70L
size of the house
MACHINE LEARNING
Learning from Data
• we are on a task to built a app recommendation system with some previous data
• what do think can be criteria that influences the recommendation more , gender or age
• There is not much split in gender
• If we use the age split we see people below age 20 downloaded pubg and other downloaded
whatsapp and snapchat
• we can decide the following algorithm
• This is known as decision tree learning and we will study this in detail in upcoming sections
age
Gender Age App
F 15 pubg
pubg gender
F 25 whatsapp F
M
M 32 snapchat
F 40 whatsapp snapchat whatsapp
M 12 pubg
M 14 pubg
MACHINE LEARNING
The new dawn of Machine Learning and Artificial Intelligence
https://insights.nikkoam.com/articles/2019/12/whats_causing_the_exponential
MACHINE LEARNING
Some facts about the career in this field
MACHINE LEARNING
Some facts about the career in this field
MACHINE LEARNING
Some facts about the career in this field
