Name: SABARNA ROY

Department: MCA
Subject: MCAN-E304F
Roll no.: 05

Topic: Neural Network

 Index

 Introduction

 Establishment of Neural
Network

 Applications and different terms

and types

 Conclusion
 Reference
 Introduction

In this report is discuss above “Neural

Network” and it’s terminology, different
aspects, types , usage , and it’s impacts
on modernized lifes .
Neural networks are computing systems
with interconnected nodes that work
much like neurons in the human brain.
Using algorithms, they can recognize
hidden patterns and correlations in raw
data, cluster and classify it, and over
time – continuously learn and improve.
The original goal of the neural network
approach was to create a computational
system that could solve problems like a
human brain. However, over time,
researchers shifted their focus to using
neural networks to match specific tasks,
leading to deviations from a strictly
biological approach. Since then, neural
networks have supported diverse tasks,
including computer vision, speech
recognition, machine translation, social
network filtering, playing board and
video games, and medical diagnosis.

As structured and unstructured data

sizes increased to big data levels,
people developed deep learning systems,
which are essentially neural networks
with many layers. Deep learning enables
the capture and mining of more and
bigger data, including unstructured data.
----------------------------------------
---------------------
 Establishment of “Neural
Network”

The first neural network was conceived

of by Warren McCulloch and Walter Pitts
in 1943. They wrote a seminal paper on
how neurons may work and modeled
their ideas by creating a simple neural
network using electrical circuits.
This breakthrough model paved the way
for neural network research in two areas:

 Biological processes in the brain

 The application of neural networks
to artificial intelligence(AI).
AI research quickly accelerated, with
Kunihiko Fukushima developing the first
true, multilayered neural network in
1975.

----------------------------------------
---------------------
Applications and Different
terms and types

Neural networks are also ideally suited

to help people solve complex problems
in real-life situations. They can learn
and model the relationships between
inputs and outputs that are nonlinear
and complex; make generalizations and
inferences; reveal hidden relationships,
patterns and predictions; and model
highly volatile data (such as financial
time series data) and variances needed
to predict rare events (such as fraud
detection). As a result, neural networks
can improve decision processes in areas
such as:
 Credit card and Medicare fraud detection.
 Optimization of logistics for
transportation networks.
 Character and voice recognition, also
known as natural language processing.
 Medical and disease diagnosis.
 Targeted marketing.
 Financial predictions for stock prices,
currency, options, futures, bankruptcy
and bond ratings.
 Robotic control systems.
 Electrical load and energy demand
forecasting.
 Process and quality control.
 Chemical compound identification.
 Ecosystem evaluation.
 Computer vision to interpret raw photos
 and videos (for example, in medical
imaging and robotics and facial
recognition).

Types of Neural Networks :-

There are different kinds of deep neural

networks – and each has advantages and
disadvantages, depending upon the use.
Examples include:

1. Convolutional neural networks

(CNNs) = It contain five types of
layers- input, convolution, pooling,
fully connected and output. Each
layer has a specific purpose, like
summarizing, connecting or
activating. Convolutional neural
networks have popularized image
classification and object detection.
However, CNNs have also been
 applied to other areas, such as
natural language processing and
forecasting.

2. Recurrent neural networks

(RNNs) = It use sequential
information such as time-stamped
data from a sensor device or a spoken
sentence, composed of a sequence of
terms. Unlike traditional neural
networks, all inputs to a recurrent
neural network are not independent
of each other, and the output for each
element depends on the
computations of its preceding
elements. RNNs are used in
fore¬casting and time series
applications, sentiment analysis and
other text applications.

3. Feedforward neural networks, in

 which each perceptron in one layer is
connected to every perceptron from
the next layer. Information is fed
forward from one layer to the next in
the forward direction only. There are
no feedback loops.

4. Autoencoder neural networks are

used to create abstractions called
encoders, created from a given set of
inputs. Although similar to more
traditional neural networks,
autoencoders seek to model the
inputs themselves, and therefore the
method is considered unsupervised.
The premise of autoencoders is to
desensitize the irrelevant and
sensitize the relevant. As layers are
added, further abstractions are
formulated at higher layers (layers
closest to the point at which a
decoder layer is introduced). These
 abstractions can then be used by
linear or nonlinear classifiers.

5. Perceptron= This model, proposed

by Minsky Papert is one of the
simplest and oldest models of neuron.
It is the smallest unit of neural
network that does certain
computations to detect features or
business intelligence in the input
data.It accepts weighted inputs, and
apply the activation function to obtain
the output as the final result.
Perceptron is also known as
TLU( threshold logic unit). It is a
supervised learning algorithm that
classifies the data into two
categories ,thus it is binary classifier.
A perceptron separates the input
space into two categories by a
hyperplane represented by this
equation:
 W pow(T) + Bi =0
6. Multilayer Perceptron= It’s
application are speech recognition,
machine translation, complex
classification. An entry point towards
complex neural nets where input data
travels through various layers of
artificial neurons. Every single node
is connected to all neurons in the next
layer which makes it a fully
connected neural network. Input and
output layers are present having
multiple hidden layers i.e. at least
three or more layers in total. It has a
bi-directional propagation i.e.
forward propagation and backward
propagation.
Inputs are multiplied with weights
and fed to the activation function and
in back propagation, they are
modified to reduce the loss. In simple
words, weights are machine learnt
values from neural networks. They
self adjust depending on the
difference between predicted outputs
versus training inputs. Nonliner
activation functions are used
followed by softmax as an output
layer activation function.

A simple neural network includes an

input layer, an output (or target)
layer and, in between, a hidden layer.
The layers are connected via
nodes,and these connections form a
“network” the neural network –of
interconnected nodes.

Conclusion
By this report extract abouts of Neural
Network and its usages. This report is
sort and approximately brief of Neural
Network . This subject is newly introduce
,and it’s research and development is
still progressing in various science and
researcher institutes. Day by day newly
invented theories and models are we get
by scholars , and human are steps
toward the new technology and resolves
their daily hindrance.
Public sector solutions

Retail
The retail industries uses neural networks to power conversational chatbots,

----------------------------------------
--------------------
hance and deepen customer intelligence, and perform network analysis.

Retail solutions
Learn more about industries using this technology

Reference
  AI for Data Science
-By Zacharias Voulgaris
(Book)

 LinkedIn

----------------------------------------
---------------------