INTRODUCTION

TO
MACHINE
LEARNING
PRESENTED
BY :-
KISHAN
KUMAR RAI
B.TECH,CSE
6TH SEM
Have You Ever Wondered ?

 How Google classifies yours mails as Spam/Non-Spam?

Have You Ever Wondered ?

 How Google translate to more than 100 languages ?

Have You Ever Wondered ?

 How the Self-Driving cars are made ?

Have You Ever Wondered ?

 How Siri, Cortana gives you correct replies ?

Have You Ever Wondered ?

 How the products are recommended/advertises on sites ?

 What
Is
Machine
Learning ?
Machine Learning is the subfield
of the Artificial intelligence(AI)that
provides system the ability to
automatically learn and improve from
experience without being explicitly
programmed.
Machine Learning focuses on the
development of computer program
that can access the data and use it
learn for themselves.
 History of Machine Learning

 The term Machine Learning was coined by

Arthur Samuel in 1959, an American
pioneer in the field of computer gaming
and artificial intelligence and stated that

 “It gives computers the ability to learn

without being explicitly programmed”.

 And in 1997, Tom Mitchell gave a “well-

posed” mathematical and relational
definition that

 “A computer program is said to learn from

experience E with respect to some task T
and some performance measure P, if its
performance on T, as measured by P,
improves with experience E.”
Why Do We Need Machine Learning?
We need machine learning for tasks that are too complex for humans to code directly, i.e. tasks that
are so complex that it is impractical, if not impossible, for us to work out all of the nuances and code
for them explicitly. So instead, we provide a machine learning algorithm with a large amount of data
and let it explore and search for a model that will work out what the programmers have set out to
achieve.

Let’s look at these two examples:

 It’s very hard to write programs that solve problems like recognizing a 3D object, from a novel
viewpoint, in new lighting conditions, in a cluttered scene. We don’t know what program to write
because we don’t know how it’s done in our brain. Even if we had a good idea for how to do it, the
program might be horrendously complicated.
 It’s hard to write a program to compute the probability that a credit card transaction is fraudulent.
There may not be any rules that are both simple and reliable. We need to combine a very large
number of weak rules. Fraud is a moving target, but the program needs to keep changing.
 Machine learning vs traditional learning
 Traditional programming differs
significantly from machine learning. In
traditional programming, a programmer
code all the rules in consultation with an
expert in the industry for which software
is being developed. Each rule is based
on a logical foundation; the machine will
execute an output following the logical
statement. When the system grows
complex, more rules need to be written.
It can quickly become unsustainable to
maintain.

 Machine learning is supposed to

overcome this issue. The machine learns
how the input and output data are
correlated and it writes a rule. The
programmers do not need to write new
rules each time there is new data. The
algorithms adapt in response to new
 How does Machine learning work?
Machine learning is the brain where all the learning takes place. The way the machine learns
is similar to the human being. Humans learn from experience. The more we know, the more
easily we can predict. By analogy, when we face an unknown situation, the likelihood of
success is lower than the known situation. Machines are trained the same. To make an
accurate prediction, the machine sees an example. When we give the machine a similar
example, it can figure out the outcome. However, like a human, if its feed a previously unseen
example, the machine has difficulties to predict.
The life of Machine Learning programs is
straightforward and can be summarized in the
following points:
 Define a question
 Collect data
 Visualize data
 Train algorithm
 Test the Algorithm
 Collect feedback
 Refine the algorithm
 Loop 4-7 until the results are satisfying
 Use the model to make a prediction
 Supervised machine learning
algorithms can apply what has been learned in the past to new data using labeled
examples to predict future events. Starting from the analysis of a known training dataset,
the learning algorithm produces an inferred function to make predictions about the
output values. The system is able to provide targets for any new input after sufficient
training. The learning algorithm can also compare its output with the correct, intended
output and find errors in order to modify the model accordingly.

Key points:
 Regression and classification problems are
mainly solved here.
 Labelled data is used for training here.
 Popular Algorithms: Linear Regression, Support
Vector Machines (SVM), Neural Networks,
Decision Trees, Naive Bayes, Nearest Neighbor.
 It is mainly used in Predicting Modelling.
 Regression:
This is a type of problem where we need to predict the continuous-
response value (ex : above we predict number which can vary from
-infinity to +infinity).
Some examples are :
 what is the price of house in a specific city?
 what is the value of the stock?
 how many total runs can be on board in a cricket game?
 etc… there are tons of things we can predict if we wish.

 Classification:
This is a type of problem where we predict the categorical
response value where the data can be separated into specific
“classes” (ex: we predict one of the values in a set of values).
Some examples are :
 this mail is spam or not?
 will it rain today or not?
 is this picture a cat or not?
 Basically ‘Yes/No’ type questions called binary classification.
 Other examples are :
 this mail is spam or important or promotion?
 is this picture a cat or a dog or a tiger?
 This type is called multi-class classification.
 unsupervised machine
learning
algorithms are used when the information used to
train is neither classified nor labeled. Unsupervised
learning studies how systems can infer a function to
describe a hidden structure from unlabeled data. The
system doesn’t figure out the right output, but it
explores the data and can draw inferences from
datasets to describe hidden structures from unlabeled
data.

Key points:
 It is used for Clustering problems(grouping), Anomaly
Detection (in banks for unusual transactions) where
there is a need for finding relationships among the data
given.
 Unlabeled data is used in unsupervised learning.
 Popular Algorithms: k-means clustering, Association
rule.
 It is mainly used in Descriptive Modelling.
 Clustering:
This is a type of problem where we group similar things together.
Bit similar to multi class classification but here we don’t provide the labels, the
system understands from data itself and cluster the data.
Some examples are :
 given news articles,clustre into different types of news
 given a set of tweets ,cluster based on content of tweet
 given a set of images, cluster them into different objects
 Reinforced Machine
Learning:
The machine is exposed to an environment where it gets trained by trial and
error method, here it is trained to make a much specific decision. The machine
learns from past experience and tries to capture the best possible knowledge
to make accurate decisions based on the feedback received.

Key points:
 Basic reinforcement is modelled as
Markov Decision Process
 The most popular algorithms used here
is Q-Learning, Deep Adversarial
Networks.
 Its practical applications include
computer playing board games such as
chess and GO, Self-driving cars also use
this learning.
 What are Neural Networks?
Neural Networks are a class of models within the general machine
learning literature. Neural networks are a specific set of
algorithms that have revolutionized machine learning. They are
inspired by biological neural networks and the current so-called
deep neural networks have proven to work quite well. Neural
Networks are themselves general function approximations, which
is why they can be applied to almost any machine learning
problem about learning a complex mapping from the input to the
output space.

 Here are the three reasons you should study

neural computation:
 To understand how the brain actually works: it’s very big and
very complicated and made of stuff that dies when you poke it,
so we need to use computer simulations.
 To understand a style of parallel computation inspired by
neurons and their adaptive connections: it’s a very different
style from sequential computation.
 To solve practical problems by using novel learning algorithms
inspired by the brain: learning algorithms can be very useful
Applications
of
Machine
Learning
 Traffic Alerts (Maps)
Now, Google Maps is probably THE app we use whenever we go out and require assistance in
directions and traffic. The other day I was traveling to another city and took the expressway
and Maps suggested: “Despite the Heavy Traffic, you are on the fastest route“. But, How does
it know that?

 Products Recommendations
Suppose you check an item on Amazon, but you do not buy it then and there. But
the next day, you’re watching videos on YouTube and suddenly you see an ad for the
same item. You switch to Facebook, there also you see the same ad. So how does
this happen?
 Virtual Personal Assistants
As the name suggests, Virtual Personal Assistants assist in finding useful
information, when asked via text or voice. Few of the major Applications of
Machine Learning here are:

 Speech Recognition
 Speech to Text Conversion
 Natural Language Processing
 Text to Speech Conversion

 Self Driving Cars

Well, here is one of the coolest application of Machine Learning. It’s here and people are
already using it. Machine Learning plays a very important role in Self Driving Cars and I’m
sure you guys might have heard about Tesla. The leader in this business and their current
Artificial Intelligence is driven by hardware manufacturer NVIDIA, which is based on
Unsupervised Learning Algorithm.
 Machine Learning Achievement
 In 2002, IBM develop the IBM WATSON which beats the two human in a game
JEOPARDY.it
is the result of machine learning ,natural language processing and information
retrieval technology.
 Machine Learning Achievement
 In 2002, IBM develop the IBM WATSON which beats the two human in a game
JEOPARDY.it
is the result of machine learning ,natural language processing and information
retrieval
 In technology.
2016,Google AlphaGo program become the first computer program to
beat a professional human using the combination of Machine Learning
and Tree Search Techniques.
 Machine Learning Achievement