Machine Learning in Layman's Terms
L
e
s
s
o
n
:
1
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
(
L
a
y
m
a
n
’
s
t
e
r
m
)
[ For understanding Deep Learning, first we need to know what is Machine Learning.
In this lesson, we will try to understand machine learning from a 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?
4
It is a CAR
L
e
t
u
s
a
s
k
t
h
e
s
a
m
e
q
u
e
s
t
i
o
n
t
o
h
i
m
What is this object?
5
L
e
t
u
s
a
s
k
t
h
e
s
a
m
e
q
u
e
s
t
i
o
n
t
o
h
i
m
What is this object?
6
?
[
B
u
t
,
h
e
i
s
a
h
u
m
a
n
b
e
i
n
g
.
H
e
c
a
n
o
b
s
e
r
v
e
a
n
d
l
e
a
r
n
]
L
e
t
u
s
m
a
k
e
h
i
m
l
e
a
r
n
show him
8
L
e
t
u
s
m
a
k
e
h
i
m
l
e
a
r
n
show him
9
L
e
t
u
s
a
s
k
t
h
e
s
a
m
e
q
u
e
s
t
i
o
n
n
o
w
What is this object?
10
Past experience
L
e
t
u
s
a
s
k
t
h
e
s
a
m
e
q
u
e
s
t
i
o
n
n
o
w
What is this object?
11
CAR
Machines follow instructions
12
W
h
a
t
a
b
o
u
t
a
M
a
c
h
i
n
e
?
[ It can not take decision of its own]
Machines follow instructions
13
W
h
a
t
a
b
o
u
t
a
M
a
c
h
i
n
e
?
We can ask a machine
•
To perform an arithmetic operations such as
•
Addition
•
Multiplication
•
Division
Machines follow instructions
14
W
h
a
t
a
b
o
u
t
a
M
a
c
h
i
n
e
?
•
Comparison
•
•
Plotting a chart
[ But, we can ask a machine
to make a decision of its own ]
15
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
[ We want a machine to act like a human]
16
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
[ to identify this object.]
17
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
[ predict the price in future]
Price in 2025?
18
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
[ Natural Language understand, and correct grammar ]
I
made
met
him yesterday
19
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
recognize face
[ Recognize Faces ]
20
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
[ What do we do?
Just like, what we did to human,
we need to provide experience
to the machine.
]
21
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
Dataset
[
This what we called as Data
or Training dataset
So, we first need to provide
training dataset to the
machine
]
+
22
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
Dataset
+
[ Then, devise algorithms and execute programs on the
data
With respect to the underlying target tasks ]
+
23
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
Dataset
+
[ Then, using the programs, Identify
required rules ]
+
+
24
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
Dataset
+
[extract required patterns ]
+
+
25
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
Dataset
+
[ Identify relations ]
+
+
26
W
h
a
t
i
s
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
?
Dataset
+
[ So that machine can derive inferences
from the data ]
+
+
=
I
n
s
u
m
m
a
r
y
,
w
h
a
t
i
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
?
27
Given a machine learning problem
•
Identify and create the appropriate dataset
•
Perform computation to learn
•
Required rules, pattern and relations
•
Output the decision
Machine Learning Paradigms
•
Supervised
•
Unsupervised Learning
•
Reinforcement learning
28
[ 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 ]
What is Supervised Learning?
29
[In supervised learning, we need some thing called a Labelled Training Dataset ]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
=
Training Dataset
What is Supervised Learning?
30
[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
=
Training Dataset
What is Supervised Learning?
31
[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
=
Training Dataset
What is Supervised Learning?
32
[ Given a labelled dataset, the task is to devise a function which takes the dataset, and a new sample, and
produces an output value.]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
=
Training Dataset
What is Supervised Learning?
33
[ If the possible output values of the function are predefined and discrete/categorical, it is called
Classification
CAR
CAR
BIKE
BIKE
Samples
+
Labels
=
Training Dataset
Classification
What is Supervised Learning?
34
[ 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 ]
CAR
CAR
BIKE
BIKE
Samples
+
Labels
=
Training Dataset
Classification
Classifier
35
Elephant
Tiger
Dataset
Identify the Animal ?
Classifier
Elephant
Regression
36
Dataset
[ If the possible output values of the function are continuous real values, then it is called Regression
Regression
37
[
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
]
What is Unsupervised Learning
38
Dataset
[ In the unsupervised learning, we do not need to know the labels or Ground truth values ]
CAR
CAR
BIKE
BIKE
What is Unsupervised Learning
39
Dataset
[ The task is to identify the patterns like group the similar objects together ]
Clustering
What is Unsupervised Learning
40
Dataset
[ Association rules like ]
Association Rules Mining
More Example Unsupervised Learning
41
Dataset
More Example Unsupervised Learning
42
Dataset
43
More Example Unsupervised Learning
What is Reinforcement Learning
44
[ It is also known as learning from trials and errors ]
What is Reinforcement Learning
45
What is Reinforcement Learning
46
What is Reinforcement Learning
47
Another Example
48
Agent
Task
Environment
Reinforcement Learning
49
Punishment
Reinforcement Learning
50
Reward
Reinforcement Learning
51
Reward
Baby Learn from the Trials and Errors
Reinforcement Learning
Summary
[ In this lesion, we have learnt ]
what is machine learning
what are the machine learning paradigms
Delve into the concept of machine learning by exploring how humans learn from past experiences to make decisions, contrasting this with how machines follow instructions without making decisions on their own. Discover the fundamental difference between human and machine learning through easy-to-understand examples and visuals.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Lesson Lesson: 1 : 1 What is Machine Learning? What is Machine Learning? (Layman s term) (Layman s term) [ For understanding Deep Learning, first we need to know what is Machine Learning. In this lesson, we will try to understand machine learning from a Layman s term.]
Human can learn from past experience and make decision of its own 2
What is this object? CAR CAR BIKE It is a CAR BIKE 4
Let us ask the same question to him Let us ask the same question to him What is this object? 5
Let us ask the same question to him Let us ask the same question to him What is this object? ? 6
[ But, he is a human being. He can observe and [ But, he is a human being. He can observe and learn ] learn ]
Let us make him learn Let us make him learn show him 8
Let us make him learn Let us make him learn CAR show him CAR BIKE BIKE 9
Let us ask the same question now 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 Let us ask the same question now What is this object? CAR CAR CAR BIKE BIKE 11
What about a Machine ? What about a Machine ? Machines follow instructions [ It can not take decision of its own] 12
What about a Machine ? 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 ? What about a Machine ? Comparison Print Plotting a chart Machines follow instructions [ But, we can ask a machine to make a decision of its own ] 14
What is Machine Learning? What is Machine Learning? [ We want a machine to act like a human] 15
What is Machine Learning? What is Machine Learning? [ to identify this object.] 16
What is Machine Learning? What is Machine Learning? Price in 2025? [ predict the price in future] 17
What is Machine Learning? What is Machine Learning? I made met him yesterday [ Natural Language understand, and correct grammar ] 18
What is Machine Learning? What is Machine Learning? recognize face [ Recognize Faces ] 19
What is Machine Learning? 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? 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? 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? What is Machine Learning? + + + Dataset [ Then, using the programs, Identify required rules ] 23
What is Machine Learning? What is Machine Learning? + + + Dataset [extract required patterns ] 24
What is Machine Learning? What is Machine Learning? + + + Dataset [ Identify relations ] 25
What is Machine Learning? What is Machine Learning? + = + + Dataset [ So that machine can derive inferences from the data ] 26
In summary, what is machine learning? 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 + =Training Dataset BIKE BIKE Labels Samples [In supervised learning, we need some thing called a Labelled Training Dataset ] 29
What is Supervised Learning? CAR CAR + ?( , )= =Training Dataset BIKE BIKE Labels Samples [ 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 + ?( , )= =Training Dataset BIKE BIKE Labels Samples [ 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 + ?( , )= CAR =Training Dataset BIKE BIKE Labels Samples [ 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 + ?( , )= CAR =Training Dataset BIKE BIKE Labels Samples [ 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 + ?( , )= CAR =Training Dataset BIKE BIKE Labels Samples [ 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 Identify the Animal ? Tiger Dataset 35
Regression Regression ?( , )= 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
What is Reinforcement Learning [ It is also known as learning from trials and errors ] 44
Another Example Agent Environment Task 48
Reinforcement Learning Punishment 49
Reinforcement Learning Reward 50
