Lesson: 1

What is Machine Learning?

(Layman’s term)
Human can learn from past experience
and make decision of its own

2
What is this object?

3
 What is this object?

CAR

CAR

BIKE
It is a CAR
BIKE

4
Let us ask the same question to him
What is this object?

5
Let us ask the same question to him
What is this object?
?

6
[ But, he is a human being. He can observe and
learn ]
Let us make him learn

show him

8
Let us make him learn

CAR

show him

CAR

BIKE

BIKE

9
Let us ask the same question now
What is this object?

CAR

CAR

BIKE
BIKE
Past experience 10
Let us ask the same question now
CAR What is this object?

CAR

CAR

BIKE
BIKE

11
What about a Machine ?

Machines follow instructions

[ It can not take decision of its own]

12
What about a Machine ?

We can ask a machine

• To perform an arithmetic operations such as

• Addition
• Multiplication
• Division

Machines follow instructions

13
What about a Machine ?

• Comparison

• Print

• Plotting a chart

Machines follow instructions

14
What is Machine Learning?

[ We want a machine to act like a human]

15
What is Machine Learning?

[ to identify this object.]

16
What is Machine Learning?

Price in 2025?

[ predict the price in future]

17
 What is Machine Learning?

I made met him yesterday

[ Natural Language understand, and correct grammar ]

18
 What is Machine Learning?

recognize face

[ Recognize Faces ]
19
What is Machine Learning?

[ What do we do?

Just like, what we did to human,

we need to provide experience

to the machine.

20
What is Machine Learning?

[
This what we called as Data
or Training dataset

+ So, we first need to provide

training dataset to the
machine
]

Dataset

21
What is Machine Learning?

+ +
[ Then, devise algorithms and execute programs on the
data

With respect to the underlying target tasks ]

Dataset

22
What is Machine Learning?

+ + +

Dataset [ Then, using the programs, Identify

required rules ]
23
What is Machine Learning?

+ + +

Dataset [extract required patterns ]

24
What is Machine Learning?

+ + +

Dataset [ Identify relations ]

25
What is Machine Learning?

+ + + =

Dataset [ So that machine can derive inferences

from the data ]
26
In summary, what is machine learning?

Given a machine learning problem

• Identify and create the appropriate dataset

• Perform computation to learn

• Required rules, pattern and relations

• Output the decision

27
 Machine Learning Paradigms
• Supervised

• Unsupervised Learning

• Reinforcement learning

[ We as human being solve various types of problem in our day-to-day life, <pause> Various decisions
need to be taken.
Depending on the nature of the problem, machine learning tasks can be broadly divided in ]
28
What is Supervised Learning?
CAR

CAR

+ BIKE
= Training Dataset
BIKE

Samples Labels

[In supervised learning, we need some thing called a Labelled Training Dataset ]
29
What is Supervised Learning?
CAR

CAR

+ BIKE
= Training Dataset 𝑓( , )=
BIKE

Samples Labels

[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
30
What is Supervised Learning?
CAR

CAR

+ BIKE
= Training Dataset 𝑓( , )=
BIKE

Samples Labels

[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
31
What is Supervised Learning?
CAR

CAR

+ BIKE
= Training Dataset 𝑓( , )= CAR
BIKE

Samples Labels

[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
32
What is Supervised Learning?
CAR
Classification
CAR

+ BIKE
= Training Dataset 𝑓( , )= CAR
BIKE

Samples Labels

[ If the possible output values of the function are predefined and discrete/categorical, it is called
Classification
33
What is Supervised Learning?
CAR
Classification
CAR

+ BIKE
= Training Dataset 𝑓( , )= CAR
BIKE

Samples Labels

[ Predefined classes means, it will produce output only from the labels defined in the dataset. For example,
even if we input a bus, it will produce either CAR or BIKE ]
34
Classifier
Elephant
Elephant

Classifier

Tiger Identify the Animal ?

Dataset
35
Regression
Regression

𝑓( , )= 20500.50

Dataset

[ If the possible output values of the function are continuous real values, then it is called Regression
36
[
The classification and Regression problems are supervised, because the decision depends on the
characteristics of the ground truth labels or values present in the dataset, which we define as experience
]

37
What is Unsupervised Learning
CAR

CAR

BIKE

BIKE

Dataset

[ In the unsupervised learning, we do not need to know the labels or Ground truth values ]
38
What is Unsupervised Learning

Clustering
Dataset

[ The task is to identify the patterns like group the similar objects together ]
39
What is Unsupervised Learning

Association Rules Mining

Dataset

[ Association rules like ]

40
More Example Unsupervised Learning

Dataset
41
More Example Unsupervised Learning

Dataset
42
More Example Unsupervised Learning

43
What is Reinforcement Learning

[ It is also known as learning from trials and errors ]

44
What is Reinforcement Learning

45
What is Reinforcement Learning

46
What is Reinforcement Learning

47
Another Example

Agent Task Environment

48
Reinforcement Learning

Punishment

49
Reinforcement Learning

Reward

50
Reinforcement Learning

Reward
Baby Learn from the Trials and Errors

Reinforcement Learning 51
Summary

what is machine learning

what are the machine learning paradigms

[ In this lesion, we have learnt ]