Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 11

Neural

Networks

Presented By:
Unati Dadlani (04161913049)
Contents

Introduction
Biological VS Neural Networks
Neural Network Architecture
Neural Network Examples
Advantages of Neural Networks
Conclusion
Research Paper

An Overview Of Neural Networks

Authors: Mohaiminul Islam, Guorong Chen, Shangzhu Jin

Published At: School of Intelligent Technology and Engineering, Chongqing University of


Science and Technology, Chongqing, China

Published Date: 29 - June - 2019

Link: http://www.sciencepublishinggroup.com/j/ajnna
Neural networks represent a brain metaphor
for information processing. These models
are biologically inspired rather than an
exact replica of how the brain function.

It is Composed of large number of highly


interconnected processing elements called
Introduction neurons.

Neural networks have been shown to be


very promising systems in many
forecasting applications and business
classification applications due to their
ability to learn from the data.

BRAIN MACHINE
Biological

VS

Neural
Network
Continued

In its simplest form, a


biological brain is a
huge collection of Taking inspiration
neurons. Each neuron from the brain, an
takes electrical and artificial neural
chemical signals as network is a
inputs through its collection of
many dendrites and connected units, also
transmits the output called neurons. The
signals through its connection between
axon. Axons contact the neurons can carry
other neurons at signals between them.
specialized junctions Each connection
called synapses where carries a real number
they pass on their value which
output signals to other determines the
neurons to repeat the weight/strength of the
same process over and signal.
over millions and
millions of times.
Neural Network Architecture

Input Layer
Output Layer

Data
Hidden Layers
Continued

Neural Network Architecture Includes three types of layers:

1: Input Layer:
It contains artificial neurons which receive input from the outside world on which the network will
learn, recognize about, or otherwise process.

2: Output Layer:
It contains units that respond to the information about how it learn any task.

3: Hidden Layer:
These units are in between input and output layers. The hidden layer’s job is to transform the input
into something that the output unit can use somehow.
 Google Translate

Neural  Speech Recognition


Networks
Examples  Fingerprint

 Face Recognition
Advantages of Neural Networks

A neural network can perform tasks that a linear program can


not.
When an element of the neural network fails, its parallel nature
can continue without any problem.
A neural network learn by examples and reprogramming is not
necessary.

It is easy to implement

It involves human like thinking.


•Neural Networks are inspired by the
learning processes that take place in
biological system. The computing world
has a lot to gain from neural networks.
Their ability to learn by example makes
Conclusion them very flexible and powerful.
Furthermore, there is no need to devise
an algorithm in order to perform a
specific task.

You might also like