1.
Seminar on Machine Learning
Submitted to:
Prof. Manmindar Singh
Submitted by:
Rahul Kumar Gcs-1630043
Aquif Zubair Gcs-1630051
1

2.
Agenda
 Introduction
 Basics
 Advantages
 Applications
 Classification
 Clustering
 Regression
 Use-Cases
2

3.
Quick
Questions….
 How many people have heard about machine
learning.
 How many people know about Machine learning.

4.
Machine Learning
4

5.
About
 Subfield of Artificial Intelligence(AI)
 Name is derived from the concept that it deals with
“construction and study of systems that can learn from
data ” can be seen as building blocks to make computer
learn to behave more intelligently.

6.
The main advantage of ML
 Learning and writing an algorithm
 Its easy for human brain but it is tough for machine.it
takes some time and good amount of training data for
machine to accurately classify objects.
 Implementation and automation
• This is easy for a Machine. Once learnt a machine can
process one million images without any fatigue where as
human brain can’t.
• That’s why ML with big data is a deadly combination.
6

7.
Applications of Machine
Learning
 Banking / Telecom / Retail
 Identify:
 prospective customers
 Dissatisfied customers
 Good customers
 Bad payers
 Obtain:
 More effective advertising
 Less credit risk
 Fewer fraud
7

8.
Applications of Machine
Learning
 Biomedical / Biometrics
 Medicine:
 screening
 Drug discovery
 Security:
 Face recognition
 Signature / iris verification
 fingerprinting
8

9.
Let’s dig deep
into it….
What do you mean by
Apple

10.
Learning
(Training)

11.
Categories
• Supervised Learning
• Unsupervised Learning
• Semi-Supervised Learning
• Reinforcement Learning

12.
Supervised Learning
 The correct classes of the training data are known
12

13.
Unsupervised Learning
 The correct classes of the training data are not Known
13

14.
Semi-Supervised Learning
 A Mix of Supervised and Unsupervised learning
14

15.
Reinforcement Learning
 Allows the machine or software agent to learn its behavior based on
feedback from the environment.
 This behavior can be learnt once and for all, or keep adapting as time
goes by
15

16.
Machine Learning
Techniques

17.
Techniques
Classification: predict class
from observations
Clustering: group observation
into “meaningful” group
Regression(presdiction):predi
ct value from observations.
17

18.
Classification
 Classify a document into a predefined
category.
 Documents can be text, images.
 The main goal of classification is to predict
the target class(yes/no).
 Considering the student profile to predict
whether the student will pass or fail.
18

19.
Similar/ Duplicate Images
19

20.
Clustering
 Clustering is the task of grouping a set of
objects in such a way that objects in the
same group (called a cluster) are more
similar to each other
 Objects are not predefined
 For e.g. these Keywords
--”man’s shoe”
--”Women’s shoe”
--”women’s t-shirt”
--”man’s t-shirt”
--can be cluster into 2 categories “shoe” and
“t-shirt” or “man” and “women”
20

21.
Regression
 Is a measure of the relation between the mean value of
one variable (e.g. output) and corresponding values of
other variables (e.g. time and cost)
 Regression analysis is a statistical process for estimating
the relationship among variables.
 Regression means to predict the output value using
training data.
 Popular one is Logistic regression (binary regression)
21

22.
Classification vs Regression
Classification
 Classification means to
group the output into
class.
 Classification to predict
the type of humor i.e.
harmful or not harmful
using training data.
 If it is
discrete/categorical
variable ,then it is
classification problem
Regression
 Regression means to
predict the output value
using training data.
 Regression to predict
the house price from
training data.
 If it is real
number/continuous then
it is regression problem.
22

23.
Classification vs Regression
23

24.
Let’s see the
usages in real life
Of machine learning

25.
Use- cases
 Spam Email Detection
 Machine Translation(Language Translation)
 Image Search(Similarity)
 Clustering(K Means):Amazon
 Classification : Google News
 Rating a Review
 Face Detection—Facebook’s photo tagging
 Fraud detection :Credit Card Providers
25

26.
Questions ???
26

27.
Thanks!
27