Machine learning (ML) is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence. Machine learning algorithms build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to perform the task.[1][2]:2 Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop a conventional algorithm for effectively performing the task. Machine learning is closely related to computational statistics, which focuses on making predictions using computers. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning. Data mining is a field of study within machine learning, and focuses on exploratory data analysis through unsupervised learning.[3][4] In its application across business problems, machine learning is also referred to as predictive analytics.

1. INDRODUCTION TO MACHINE
LEARNING
BY
S. Anmita.

2. SLIDES CONTAIN ABOUT
 What is machine?
 When machine born?
 Machine as computer
 Artificial intelligence
 Machine learning
 Founder and father of machine learning
 Types of machine learning
 Applications of machine learning
 Advantages and disadvantages of machine
learning

3. WHAT IS MACHINE
 A Machine is a mechanical tool with
combination of force and power which
is used to form a energy from other
energy.
 It relief the human from stress and
workload
 These is created by man to save the
value of time.

4. WHEN MACHINE BORN?
 The machine born
from our nature
earth and from that
nature our ancestors
starts to discover
new things each day
 Then One day they
discovered a
machine from stone,
wood,bones etc..
 Our first machine
we considered as
WHEEL

5. MACHINE AS COMPUTER
 The word computer is derived from latin
word
Compute –To calculate something .
 When the human find the difficulties to do
large mathematical problems they started
to bring machine into mathematics called
computer.
 These is basic reason for the Machine as
computer
 The computer is electronic device which is
used to performs specific task with high
speed.

6. MACHINE AS COMPUTER
 These computer
was found by
CHARLES BABAGE
in 1971
 The computer is a
device which used
to slove may real-
life problem by
some set of
algorithm and
progam
 worlds first
computer is ENIAC
(Electronic
Numerical
Integrator and
Computer)

7. ARTIFICIAL INTELLIGENCE

8. ARTIFICIAL INTELLIGENCE
 Diffrence of computer and Artificial
intelligence is that
• The computer without artificial Intelligence
have to managed by programmer every time
to do some task.
• The computer withArtificial Intelligence will
do the task without human interaction and do
the task automatically with restless
• The artifical intelligence made a computer
to think itself and made to learn computer by
MACHINE LEARNING

9. MACHINE LEARNING

10. MACHINE LEARNING
 Machine learning is the part of artificial
intelligence
 Machine learning is used to perform a task
from past experience and trained from that
experience and predit the future
 Machine learning is the collections of artificial
intelligence it learn automatically and
improve from experience

11. MACHINE LEARNING WILL WORK ACTUALLY
AS
LearnPast
data
Experience
Present
data
Preditct
future data

12. FOUNDER AND FATHER OF MACHINE
LEARNING
 The father of machine
learning is Arthur Lee
Samuel
 He found machine
learning in 1959
 Samuel was born on
December 5, 1901 in
Emporia, Kansas
 Checkers-playing
Program was among
the world's first
successful self-
learning programs

13. TYPES OF MACHINE LEARNING
TypesOf
ML
Supervised
ReinforcementUnsupervised

14. SUPERVISED LEARNING
 supervised learning is the learning easist way
of learning
 In supervised Learning there have some
guider to train the machine
 Machnie learn by using labels &datasets
(general and specific hypothesis)
 we will classifies data according to past data
and present data
 Example:Classificaion and regression
 Algorithm example:Candidate elimination
algorithm

15. UNSUPERVISED LEARNING
 The other type of learning is Unsupervised
learning
 In Unsupervised learning there is no guider
to train the machine
 there is no datasets or trained datas
 these predict the output is all about by using
approximate past experience but not by
datas
 it is difficult to implement
 example: clustering&Association(sequential
covering algorithm)

16. REINFORCEMENT
 It is used to work according
Environment
 The learning is to trained for Decision
making
 these learn byitself using experience
and error
 machine learns from past experience
and try to crasp best possible result to
make decisons
 Example: markov Decision process

17. APPLICATIONS
 e-Learning(Byjus app)
 Online Shopping(Amazon,flipkart)
 e-booking(redbus,ola)
 Image and speechrecognition(chatbot)
 Predition and
extraction(Chrome,firefox)
 To find similarities(face recognition)
 Statistical approch(weather
forecasting)

18. ADVANTAGE
a) It saves the value of time
b) no human interaction needed
c) Easy to humans to handle interface
with machine
d) mutitask tendency
e) It work 24/7 to do any task
f) It is interoperable to any kind of data
and information
g) Easily identifies trends ,patterns and
environment

19. DISADVANTAGE
 Take time to generate new data
sometimes
 Time and resources is not efficient
due to some reason
 chances to occur many error
 we have to choose algorithm
carefully to implement