APEX INSTITUTE OF TECHNOLOGY

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

MACHINE LEARNING (21CSH-286)

Faculty: Prof. (Dr.) Vineet Mehan (E13038)

Lecture - 2
Supervised Learning, Unsupervised Learning DISCOVER . LEARN . EMPOWER
1
Machine Learning: Course Objectives
COURSE OBJECTIVES
The Course aims to:
1. Understand and apply various data handling and visualization techniques.
2. Understand about some basic learning algorithms and techniques and their applications, as well as
general questions related to analysing and handling large data sets.
3. To develop skills of supervised and unsupervised learning techniques and implementation of these to
solve real life problems.
4. To develop basic knowledge on the machine techniques to build an intellectual machine for making
decisions behalf of humans.
5. To develop skills for selecting suitable model parameters and apply them for designing optimized
machine learning applications.

2
COURSE OUTCOMES

On completion of this course, the students shall be able to:-

Understand machine learning techniques and computing environment that are suitable
CO1
for the applications under consideration.

3
 Unit-1 Syllabus
Unit-1 Introduction to Machine Learning
Introduction to Definition of Machine Learning, Working principles of Machine
Machine Learning Learning; Classification of Machine Learning algorithms: Supervised
Learning, Unsupervised Learning, Reinforcement Learning, Semi-
Supervised Learning; Applications of Machine Learning.
Data Pre- Data Sourcing and Cleaning, Handling Missing data, Encoding
Processing and Categorical data, Feature Scaling, Handling Time Series data; Feature
Feature Selection techniques, Data Transformation, Normalization,
Extraction Dimensionality reduction
Data Visualization Data Frame Basics, Different types of analysis, Different types of
plots, Plotting fundamentals using Matplotlib, Plotting Data
Distributions using Seaborn.

4
SUGGESTIVE READINGS
• TEXT BOOKS:
• There is no single textbook covering the material presented in this course. Here is a list of books
recommended for further reading in connection with the material presented:
• T1: Tom.M.Mitchell, “Machine Learning, McGraw Hill International Edition”.
• T2: Ethern Alpaydin,” Introduction to Machine Learning. Eastern Economy Edition, Prentice Hall of
India, 2005”.
• T3: Andreas C. Miller, Sarah Guido, Introduction to Machine Learning with Python, O’REILLY (2001).

• REFERENCE BOOKS:
• R1 Sebastian Raschka, Vahid Mirjalili, Python Machine Learning, (2014)
• R2 Richard O. Duda, Peter E. Hart, David G. Stork, “Pattern Classification, Wiley, 2nd Edition”.
• R3 Christopher Bishop, “Pattern Recognition and Machine Learning, illustrated Edition, Springer, 2006”.

5
Introduction to Machine Learning
• Humans learn from experiences.

• Whatever we learn from experiences(Good or Bad) we try to

implement/perform action correspondingly.

• Example: Driving a Car

• Initially we learn how to drive
• Then we drive
• & then we become expert

6
Introduction to Machine Learning
• Similarly machines also learn

• From where machines learn?

• Machines learn from data.

• More the data  better will be the model  higher will be the
accuracy. (Just like the more you drive  the more better you
become a driver)
By: Prof. (Dr.) Vineet Mehan 7
Introduction to Machine Learning
• ML is a branch of AI.

• Learning means
• Acquiring Knowledge
• Behavior Skills
• Understanding
• Synthesizing different information

• Ability to learn is possessed by humans, animals etc. and now this

ability to learn is extended to machines.
By: Prof. (Dr.) Vineet Mehan 8
Definition

ML is a scientific discipline that is

concerned with design and
development of algorithms that
allows computers to change
behaviors based on data.
By: Prof. (Dr.) Vineet Mehan 9
Introduction to Machine Learning
• Major focus of ML  to automatically learn to recognize complex
patterns

• And to make intelligent decisions based on the data.

• It is for the above reason that ML is closely related to the following

areas:

• 1. Statistics
By: Prof. (Dr.) Vineet Mehan 10
Introduction to Machine Learning
• Probability Theory

• AI

• Theoretical Computer Science

• Data Mining

• Pattern Recognition
By: Prof. (Dr.) Vineet Mehan 11
Types of Machine Learning
1. Supervised Learning

2. Unsupervised Learning

3. Semi-Supervised Learning

4. Reinforcement Learning

By: Prof. (Dr.) Vineet Mehan 12

 So when new weight is entered in to the model,
machine can predict the currency
1. Supervised Learning
Such a model where labeled data is used for
learning is called Supervised Learning.
• Lets say there are 2 friends

• One friend gives 1 million coins(10 Lakhs) to the another of 3 different

currencies.
So, on the basis of weights Machine can predict the
Currencies Weights
currency of the coin.
• One Rupee 4 Grams
Weights = Feature
• One Dollar 9 Grams
Currency = Label
• One Pound 3 Grams
When data is fed to the machine it learns that
which feature is associated with which label.
By: Prof. (Dr.) Vineet Mehan 13
1. Supervised Learning
• In supervised learning, we use known or labeled data for the training data.

• Since the data is known, the learning is, therefore, supervised, i.e., directed
into successful execution.

• The input data goes through the Machine Learning algorithm and is used to
train the model.

• Once the model is trained based on the known data, you can use unknown
data into the model and get a new response.
By: Prof. (Dr.) Vineet Mehan 14
1. Supervised Learning

By: Prof. (Dr.) Vineet Mehan 15

Algorithms used for Supervised Learning
• Polynomial regression
• Random forest
• Linear regression
• Logistic regression
• Decision trees
• K-nearest neighbors
• Naive Bayes

By: Prof. (Dr.) Vineet Mehan 16

2. Unsupervised Learning
• Lets say we have a cricket dataset of various players with the
respective scores and wickets taken.

• This data is feed into the ML model.

• Machine identifies the performance of players.

• It plots a graph with x axis and y axis.

By: Prof. (Dr.) Vineet Mehan 17

2. Unsupervised Learning
Wickets Runs 140
1 100
120
1 90
2 85 100

1 75 80

Wickets
1 120 60
4 30 40
5 40
20
3 24
6 29 0
0 1 2 3 4 5 6 7
4 42 Runs

By: Prof. (Dr.) Vineet Mehan 18

 Interpretation is : Data is of Batsman

2. Unsupervised Learning It shows players that have scored more

runs and taken less wickets
140
Cluster 1
120
100
80
Wickets

60
40 Cluster 2
20
0
0 1 2 3 4 5 6 7
Runs
It shows players that have scored less
runs and taken more wickets

Interpretation is : Data is of Bowlers

Important Point is: Initially there were No Labeled Learning with
no labels of batsman and bowlers Data
By: Prof. (Dr.) Vineet Mehan
No Labeled Data
19
is
Unsupervised Learning
2. Unsupervised Learning
• In unsupervised learning, the training data is unknown and unlabeled -
meaning that no one has looked at the data before.

• Without the aspect of known data, the input cannot be guided to the
algorithm, which is where the unsupervised term originates from.

• This data is fed to the Machine Learning algorithm and is used to train the
model.

• The trained model tries to search for a pattern and give the desired response.

By: Prof. (Dr.) Vineet Mehan 20

2. Unsupervised Learning

By: Prof. (Dr.) Vineet Mehan 21

3. Semi-Supervised Learning
• In this learning is obtained both from the supervised learning and
unsupervised learning.

Labeled Data
Unlabeled Data
Expensive to
Cheap to Obtain Obtain

ML Researchers  use Labeled data + Unlabeled data in

conjunction it improves learning accuracy
By: Prof. (Dr.) Vineet Mehan 22
Algorithms used for Unsupervised Learning
• Partial least squares
• Fuzzy means
• Singular value decomposition
• K-means clustering
• Apriori
• Hierarchical clustering
• Principal component analysis

By: Prof. (Dr.) Vineet Mehan 23

4. Reinforcement Learning
• Let’s say we have an image of a dog.

• Image is fed into the model.

• Model task is to identify that it is a dog.

• If model identifies it to be a dog then a positive response is there.

• If model identifies it to be a cat then a negative response is there.

By: Prof. (Dr.) Vineet Mehan 24
4. Reinforcement Learning
• Now machine learns from the feedback.

• If any other image of dog comes at a later time then the model will be
able to classify it correctly.

By: Prof. (Dr.) Vineet Mehan 25

4. Reinforcement Learning
• Reinforcement Learning is a feedback-based Machine learning
technique.

• In Reinforcement Learning an agent learns to behave in an

environment by performing the actions and seeing the results of
actions.

• For each good action, the agent gets positive feedback, and for each
bad action, the agent gets negative feedback or penalty.

By: Prof. (Dr.) Vineet Mehan 26

4. Reinforcement Learning
• In Reinforcement Learning, the agent learns automatically using
feedbacks without any labeled data, unlike supervised learning.

• Since there is no labeled data, so the agent is bound to learn by its

experience only.

• Like traditional types of data analysis, here, the algorithm discovers

data through a process of trial and error and then decides what
action results in higher rewards.

By: Prof. (Dr.) Vineet Mehan 27

Generalized Machine Learning Model
Model

Inputs Outputs
If output is right then
take the output as final
result. Else

Feedback is given to the

model to predict until it
learns.
By: Prof. (Dr.) Vineet Mehan 28
 Fig: Machine Learning Process

By: Prof. (Dr.) Vineet Mehan 29

Task: Scenario-1
• Facebook recognizes your friend in a picture from an album of tagged
photographs.

• Decide that it is Supervised/Unsupervised/ Reinforcement Learning

and support your answer with a suitable reason (BT-Level5)

By: Prof. (Dr.) Vineet Mehan 30

Task: Scenario-2
• Netflix recommends a new movie based on the past movie choices.

• Decide that it is Supervised/Unsupervised/ Reinforcement Learning

and support your answer with a suitable reason (BT-Level5)

By: Prof. (Dr.) Vineet Mehan 31

Task: Scenario-3
• Analyzing bank data for suspicious transactions and flagging fraud
transactions.

• Decide that it is Supervised/Unsupervised/ Reinforcement Learning

and support your answer with a suitable reason (BT-Level5)

By: Prof. (Dr.) Vineet Mehan 32

Summary
• Introduction

• Types of Machine Learning

• Examples

• Machine Learning Process

33
REFERENCES
• https://www.javatpoint.com/machine-learning

• https://www.tutorialspoint.com/machine_learning/index.htm

• https://
www.simplilearn.com/tutorials/machine-learning-tutorial/what-is-ma
chine-learning?source=sl_frs_nav_playlist_video_clicked

34
THANK YOU

For queries
Email: [email protected]
35