D R .

DAU D A B D U L L A H

MACHINE LEARNING L E C T U R E 1

FA L L 1 1 2 0 2 4
2
3
4
 DEFINITION
Machine Learning is the
OF MACHINE
field of study that gives the
LEARNING
computer the ability to learn
without being explicitly
programmed.
Arthur Samuel (1959)

Arthur Lee Samuel was an American

pioneer in the field of computer gaming
and artificial intelligence. He popularized
the term "machine learning" in 1959.The
Samuel Checkers-playing Program was
among the world's first successful self-
learning programs, and as such a very
early demonstration of the fundamental
concept of artificial intelligence. 5
 DEFINITION • A computer program is said to learn from experience E with
respect to some class of tasks T and performance measure
OF MACHINE P, if its performance at tasks in T, as measured by P,
LEARNING improves with experience E.
• Experience (data): games played by the program (with itself)
• Performance measure: winning rate
Tom Mitchell (1998)

Tom Michael Mitchell is an American

computer scientist and E. Fredkin
University Professor at the Carnegie
Mellon University(CMU). He is a former
Chair of the Machine Learning Department
at CMU. Mitchell is known for his
contributions to the advancement
of machine learning, artificial intelligence,
and cognitive neuroscience and is the 6
author of the textbook Machine Learning.
7
A P P L I C AT I O N S
OF MACHINE
LEARNING

8
 TRAFFIC ALERTS – GOOGLE MAPS

Now, Google Maps is probably THE app we use whenever we go out and
require assistance in directions and traffic. The other day I was traveling to
another city and took the expressway and Maps suggested: “Despite the
Heavy Traffic, you are on the fastest route“. But, How does it know that?

Well, It’s a combination of People currently using the service, Historic Data of
that route collected over time and few tricks acquired from other companies.
Everyone using maps is providing their location, average speed, the route in
which they are traveling which in turn helps Google collect massive Data
about the traffic, which makes them predict the upcoming traffic and adjust
your route according to it.

9
LARGE LANGUAGE MODELS

10
 SOCIAL MEDIA –
FA C E B O O K D E E P FA C E

One of the most common applications of Machine

Learning is Automatic Friend Tagging Suggestions in
Facebook or any other social media platform. Facebook
uses face detection and Image recognition to
automatically find the face of the person which matches
it’s Database and hence suggests us to tag that person
based on DeepFace.
Facebook’s Deep Learning project DeepFace is
responsible for the recognition of faces and identifying
which person is in the picture. It also provides Alt Tags
(Alternative Tags) to images already uploaded on
facebook. For eg., if we inspect the following image on
Facebook, the alt-tag has a description.
11
 P RO D U C T R E C O M M E N DAT I O N S

Suppose you check an item on Amazon, but you do

not buy it then and there. But the next day, you’re
watching videos on YouTube and suddenly you see
an ad for the same item. You switch to Facebook,
there also you see the same ad. So how does this
happened?
Well, this happens because Google tracks your
search history, and recommends ads based on your
search history. This is one of the coolest applications
of Machine Learning. In fact, 35% of Amazon’s
revenue is generated by Product Recommendations.

12
 V I R T U A L P E R S O N A L A S S I S TA N T S

As the name suggests, Virtual Personal Assistants assist in finding useful information, when asked via
text or voice. Few of the major applications of Machine Learning here are:

• Speech Recognition
• Speech to Text Conversion
• Natural Language Processing
• Text to Speech Conversion

All you need to do is ask a simple question like “What is my schedule for tomorrow?” or “Show my
upcoming Flights“. For answering, your personal assistant searches for information or recalls your
related queries to collect info. Recently personal assistants are being used in Chatbots which are being
implemented in various food ordering apps, online training websites and also in Commuting apps. 13
 SELF DRIVING CARS

Well, here is one of the coolest application of Machine Learning. It’s here and
people are already using it. Machine Learning plays a very important role in
Self Driving Cars and I’m sure you guys might have heard about Tesla. The
leader in this business and their current Artificial Intelligenceis driven by
hardware manufacturer NVIDIA, which is based on Unsupervised Learning
Algorithm.

NVIDIA stated that they didn’t train their model to detect people or any object
as such. The model works on Deep Learning and it crowdsources data from
all of its vehicles and its drivers. It uses internal and external sensors which are
a part of IOT. According to the data gathered by McKinsey, the automotive
data will hold a tremendous value of $750 Billion.
14
 DYNAMIC PRICING

Setting the right price for a good or service is an old problem in

economic theory. There are a vast amount of pricing strategies that
depend on the objective sought. Be it a movie ticket, a plane ticket or
cab fares, everything is dynamically priced. In recent years, artificial
intelligence has enabled pricing solutions to track buying trends and
determine more competitive product prices.

How does Uber determine the price of your ride?

Uber’s biggest uses of Machine Learning comes in the form of surge
pricing, a machine learning model nicknamed as “Geosurge”. If you
are getting late for a meeting and you need to book an Uber in a
crowded area, get ready to pay twice the normal fare. Even for
flights, if you are traveling in the festive season the chances are
prices will be twice the original price. 15
 G O O G L E T R A N S L AT E

Remember the time when you travelled to a new place and you find it difficult
to communicate with the locals or finding local spots where everything is
written in a different language.

Well, those days are gone now. Google’s GNMT(Google Neural Machine
Translation) is a Neural Machine Learning that works on thousands of
languages and dictionaries, uses Natural Language Processing to provide
the most accurate translation of any sentence or words. Since the tone of the
words also matters, it uses other techniques like POS Tagging, NER (Named
Entity Recognition) and Chunking. It is one of the best and most used
Applications of Machine Learning.
16
 ONLINE VIDEO STREAMING - NETFLIX

With over 100 million subscribers, there is no doubt that Netflix is the daddy of the online streaming
world. Netflix’s speedy rise has all movie industrialists taken aback – forcing them to ask, “How on
earth could one single website take on Hollywood?”. The answer is Machine Learning. The Netflix
algorithm constantly gathers massive amounts of data about users’ activities like:
• When you pause, rewind, or fast forward
• What day you watch content (TV Shows on Weekdays and Movies on Weekends)
• The Date and Time you watch
• When you pause and leave content (and if you ever come back)
• The ratings Given (about 4 million per day), Searches (about 3 million per day)
• Browsing and Scrolling Behavior

And a lot more. They collect this data for each subscriber they have and use their Recommender
System and a lot of Machine Learning Applications. That’s why they have such a huge customer
retention rate. 17
 FRAUD DETECTION

Experts predict online credit card fraud to soar to a

whopping $32 billion in 2020. That’s more than the profit made by Coca Cola
and JP Morgan Chase combined. That’s something to worry about. Fraud
Detection is one of the most necessary Applications of Machine Learning. The
number of transactions has increased due to a plethora of payment channels –
credit/debit cards, smartphones, numerous wallets, UPI and much more. At the
same time, the amount of criminals have become adept at finding loopholes.

Whenever a customer carries out a transaction – the Machine Learning model

thoroughly x-rays their profile searching for suspicious patterns. In Machine
Learning, problems like fraud detection are usually framed as classification
problems
18
 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 is used for the prediction of stock market
trends.

19
 MEDICAL DIAGNOSIS

In medical science, machine learning is used for diseases diagnoses. With this, medical
technology is growing very fast and able to build 3D models that can predict the exact position
of lesions in the brain.
It helps in finding brain tumours and other brain-related diseases easily.

20
M O R E A P P L I C AT I O N S O F M L
• https://www.projectpro.io/article/10-awesome-machine-learning-applications-of-
today/364
• https://builtin.com/artificial-intelligence/machine-learning-examples-applications
• https://bigdata-madesimple.com/banking-in-the-time-of-emerging-tech-
blockchain-ai-personalization/
• https://deepmind.com/research/case-studies/alphago-the-story-so-far
• https://karpathy.medium.com/software-2-0-a64152b37c35

21
RISKS OF USING ML
• Privacy Concerns
• Might lead to violation of privacy
• Security risks
• Bias problem
• Fairness problem
• Creation of fake content
• Energy Consumption

22
 TA XO N O M Y
OF MACHINE
LEARNING

A S i m p l i s t i c V i ew
B a s e d o n Ta s k s

23
 TA XO N O M Y
OF MACHINE
LEARNING

A S i m p l i s t i c V i ew
B a s e d o n Ta s k s

24
SUPERVISED
LEARNING

25
 Housing Price Prediction
Ø Given: a dataset that contains ! samples
" ! ,$ ! , … (" " ,$ " )
Ø Task: if a residence has " square feet, predict its price?

15th sample
(" ! " , $ ! " )

! = 800
%= ? 26
 Housing Price Prediction
Ø Given: a dataset that contains ! samples
" ! ,$ ! , … (" " ,$ " )
Ø Task: if a residence has " square feet, predict its price?

! = 800
%= ? 27
28
29
30
31
32
33
UNSUPERVISED
LEARNING

34
35
36
37
38
 Software 2.0 is eating Software 1.0

1000x Productivity: Google shrinks AI driven by data—

language translation code from
500k LoC to 500 lines of dataflow. not the model

• https://jack-clark.net/2017/10/09/import-ai-63-google-shrinks-language-translation-code- from-500000-to-500-lines-with-ai-only-25-of-surveyed-people-
believe-automationbetter-jobs
https://jack-clark.net/2017/10/09/import-ai-63-google-shrinks-language-translation-code-
“Software 2.0”, Andrej Karpathy, https://medium.com/@karpathy/software-2-0-a64152b37c35
• “Software 2.0”, Andrej Karpathy, https://medium.com/@karpathy/software-2-0-a64152b37c35
from-500000-to-500-lines-with-ai-only-25-of-surveyed-people-believe-automationbetter-jobs

39
… you probably used SW2.0 in the last hour…
… you probably used SW2.0 in the last hour…

Lec 15: basic theory of these new systems “Weak Supervision theory”.
Lec 15: basic Also newofcourse
theory theseonnew
ML Engineering next year!
systems “Weak Supervision theory”. 40
REINFORCEME NT
LEARNING

41
AlphaGo is a computer program that plays the board game Go. It was developed by DeepMind Technologies a subsidiary
of Google (now Alphabet Inc.). Subsequent versions of AlphaGo became increasingly powerful, including a version that
competed under the name Master. After retiring from competitive play, AlphaGo Master was succeeded by an even more
powerful version known as AlphaGo Zero, which was completely self-taught without learning from human games. AlphaGo
Zero was then generalized into a program known as AlphaZero, which played additional games, including chess and shogi.
AlphaZero has in turn been succeeded by a program known as MuZero which learns without being taught the rules.
Documentary: https://www.youtube.com/watch?v=WXuK6gekU1Y

42
43
QUESTIONS???

44
AC K N OW L E D G E M E N T !
• Various contents in this presentation have been taken from different books,
lecture notes, and the web. These solely belong to their owners, and are here used
only for clarifying various educational concepts. Any copyright infringement is
not intended.

45