Artificial Neural Network

Submitted by Submitted to
Chandana S Bhuvaneshwari K S
 Contents

• Introduction
• Definition
• Structure of ANN
• Working of ANN
• Types of ANN
• Applications
• Conclusion
 Introduction

• Artificial Neural Network(ANN) has provide an exciting

alternative method for solving a variety of problems in
different fields of science and engineering.
• A neural network is made of artificial neurons that receive and
process input data.
 Definition

• An artificial neural network is an attempt to simulate the

network of neurons that make up a human brain so that the
computer will be able to learn things and make decisions in a
humanalike manner.
• It is a computational system inspired by the
o Structure
o Processing method
o Learning ability of a biological brain
Structure of ANN
ANNs are composed of
multiple nodes, which imitate
biological neurons of human
brain. The neurons are
connected by links and they
interact with each other. The
nodes can take input data and
perform operations on the
data. The result of these
operations is passed to other
neurons. The output at each
node is called its activation or
node value.
Each link is associated with
weight. ANNs are capable of
learning, which takes place by
altering weight values.
• The terminologies used in ANN are neuron, interconnections,
net input, output
• ANN are faster in processing information and process done in
nano seconds. Instructions are executed in sequence, limited
number of neurons and information stored in memory.
 Working of ANNs

• Each row represents a connection between neurons and

indicates the pathway for the flow of information. Each
connection has a weight, an integer number that controls the
signal between neurons.
• If the network generates a good output, there is no need to
adjust the weights. If network generates a poor output then the
system alters the weights in order to improve subsequent
results.
 Types of ANN

• Feedforward ANN
• Feedback ANN

 Feedforward ANN :- In this ANN, the information flow is

undirectional. A units sends an information to other unit from
which it does not recive any information. They are used in
pattern recognition.
 Feedback ANN :- Feedback loops are allowed. They are used
in content addressable memories.
 Applications of Neural Network

• Aerospace : Autopilot aircrafts, aircraft fault detection.

• Military : Weapon steering, target tracking, facial recognition,
image identification.
• Industrial : Manufacturing process control, product design
and analysis, quality inspection system.
• Software : pattern recognition, optical character recognition
• Control : ANNs are used to make steering decisions of
vehicle.
• Telecommunications : Image and data compression,
automated information services, real-time spoken language
transaltion.
 Conclusion

Artificial Neural Networks are imitation of biological neural

networks, the computing would have a lot to gain formal neural
networks. Their ability to learn example make them very flexible
and powerful further more there is need to device an algorithm in
order to perform a specific task.
THANK YOU!!