MACHINE LEARNING INTRODUCTION

What I have learnt in this course:

1. Machine learning definition
2. Linear regression
3. Polymer regression
4. Spam email filter
5. Recommendation of app
6. Application of ML in college admission
7. Neutral network
8. Recognizing hand written digits
9. Application of deep learning
 DEFINITION OF MACHINE LEARNING:

Machine learning is a category of algorithm that allows

software applications to become more accurate in
predicting outcomes without being explicitly programmed.
The basic premise of machine learning is to build
algorithms that can receive input data and use statistical
analysis to predict an output while updating outputs as
new data becomes available.
EXAMPLE:
RENT COST OF FLAT:
We are provided with rent cost of two flats and need to
predict the rent cost of 1600sq feet flat

We need to plot the data points on x axis(sq feet) and y

axis(rent cost), we can predict the cost of the flat by
drawing a optimal line which has the minimum deviation
from the data points.

Then we will the x axis and y axis to the line and we have
found the cost of flat by using linear regression.
 LINEAR REGRESSION:
Consider three data points; we need to draw an optimal
line which has a minimum deviation from the data points.
Then we need to calculate the error function, which is the
sum of squares of the distances. To find the optimal line
we should find the minimum error function.

 POLYMER REGRESSION:

Consider a data set which is distributed as shown in the

figure and then find a optimal line but it still does not give
the minimal error in that case linear regression cannot be
 used so we use polymer regression which is of higher
order.

Let us consider a 2 degree equation; we are going to get a

curve which gives less error function

 SPAM EMAIL FILTER:

Consider a list of 100 emails; we need to figure out some

patterns to find the spam. Let’s consider the word
“discount”.
 There are 30 spam emails out of 100.then let us check
those 30 spam emails out of which 5 are not spam.

The probability of the emails to be spam if the mail is

having word “discount” is total number of spam emails by
emails with word “discount” that is equal to 25/30=0.83

 RECOMMENDED APP:
Recommendation of application is another crucial
application of ML.
 We are considering two variables i.e. gender and age
depending on these two data points, user get the app
recommendation.

We need to plot an algorithm for the above parameters.

From this way, we can build a recommendation

mechanism; even with N number of parameters we get
accurate results using ML.

 APPLICATION OF ML IN COLLEGE ADMISSIONS:

In this college admission process there are 2 steps i.e.
written test and interview.

Let us consider 3 students who want to take admission

with the score.

On what basis the college need to take the admission, for

that we need to look into previous year admission.
 On the basis of the marks acquired by the 3 students, we
can plot the data on the graph from that we get to know
whether the student is qualified for the admission or not.

The student s1 only gets the admission. This distribution is

considered as logistic regression.

Lets anaylse the case in which it has no errors

 NEURAL NETWORK:
A neural network is a series of algorithms that endeavours
to recognize underlying relationships in a set of data
through a process that mimics the way the human brain
operates. Neural networks can adapt to changing input; so
the network generates the best possible result without
needing to redesign the output criteria. The concept of
neural networks, which has its roots in artificial
intelligence, is swiftly gaining popularity in the
development of trading systems.

A neural network works similarly to the human brain’s

neural network. A “neuron” in a neural network is a
mathematical function that collects and classifies
information according to a specific architecture. The
network bears a strong resemblance to statistical methods
such as curve fitting and regression analysis.

A neural network contains layers of interconnected nodes.

Each node is a perceptron and is similar to a multiple
 linear regression. The perceptron feeds the signal
produced by a multiple linear regression into an activation
function that may be nonlinear.

 RECOGNIZING HAND WRITTEN DIGITS:

It is an application of neural network in which we have

built a system in which a computer can recognize the hand
written characters.

We are going to use a graphic stabilized by YouTube

channel 3BlueBrown.There are 4 sets of layers in which
there is one input layer and one output layer

Neuron is the thing that holds a number that can be any

number in between 0 and 1

If it is in between 0 and 1 like 0.58 then it is an activation

number.

Hidden layers play its own role i.e. lets considers 9 which is
a combination of 0 and 1 .all the characters are broken
into number of pieces. The set of information are getting
stored in the last second layer. How to recognize the
pieces it is done in the second layer. Then the last second
 layer sends the data to the output layer.

In real time there are more than 2 layers that help the
system to recognize the hand written characters.

 DEEP LEARNING:

Deep learning is a machine learning technique that

teaches computers to do what comes naturally to humans:
learn by example. Deep learning is a key technology
behind driverless cars, enabling them to recognize a stop
sign, or to distinguish a pedestrian from a lamppost. It is
the key to voice control in consumer devices like phones,
tablets, TVs, and hands-free speakers. Deep learning is
getting lots of attention lately and for good reason. It’s
achieving results that were not possible before.

In deep learning, a computer model learns to perform

classification tasks directly from images, text, or sound.
Deep learning models can achieve state-of-the-art
accuracy, sometimes exceeding human-level performance.
Models are trained by using a large set of labelled data
and neural network architectures that contain many
layers.