ARTIFICIAL NEURAL

NETWORKS

Under the Guidance of K. Venkateshwarlu.

Presented by
CONTENTS
INTRODUCTION
NEURAL NETWORK MODEL
WHY USE NEURAL NETWORKS
HOW HUMAN BRAIN LEARNS
HUMAN NEURON TO ARTIFICIAL NEURON
A SIMPLE NEURON DESCRIPTION
HOW NEURON MAKES DECISIONS
BACK PROPAGATION
APPLICATIONS
ADVANTAGES
FUTURE SCOPE
CONCLUSION
 INTRODUCTION
What are Neural Networks?
Neural networks are a new method of
programming computers.

They are exceptionally good at performing pattern

recognition and other tasks that are very difficult to
program using conventional techniques.

Programs that employ neural nets are also

capable of learning on their own and adapting to
changing conditions.
 NEURAL NETWORK MODEL

A typical neural network has

many artificial neuron called
units arranged in series.

There are input units, output

units and hidden units in
input layer, hidden layer and
output layer.
 WHY USE NEURAL NETWORKS

Neural networks, can be used to extract patterns

and detect trends that are too complex to be
noticed by either humans or other computer
techniques.
Pattern reconstruction is much more complicated
and something that on conventional computers is
very difficult to do.
For pattern reconstruction feed-forward networks
are not enough. Feedback is needed in order to
create a dynamic system that will produce the
appropriate pattern.
The output of each neuron is connected to the
input of the neighbouring neurons. These kind of
networks are called auto associative networks.
 HOW HUMAN BRAIN LEARNS
In the human brain, a typical neuron collects signals
from others through a host of fine structures called
dendrites.
The neuron sends out spikes of electrical activity
through a long, thin stand known as an axon,
which splits into thousands of branches.
At the end of each branch, a structure called a
synapse converts the activity from the axon into
electrical effects that inhibit or excite activity in the
connected neurons.
HUMAN NEURON TO ARTIFICIAL NEURON

HUMAN NEURON ARTIFICIAL NEURON

 A SIMPLE ARTIFICIAL NEURON

An artificial neuron is a
device with many inputs
and one output.

The neuron has two

modes of operation;
The Training mode and
The Using mode.
 HOW NEURON MAKES DECISIONS
Our basic computational element (model neuron)
is often called a node or unit.
It receives input from some other units, or perhaps
from an external source. Each input has an
associated weight w.
The unit computes some function f of the
weighted sum of its inputs.
The weighted sum is called the net input to unit i.
 BACK PROPAGATION
The Backpropgation algorithm searches for weight
values that minimize the total error of the network
over the set of training examples (training set).

Backpropagation consists of the repeated

application of the following two passes:
Forward pass: in this step the network is
activated on one example and the error of (each
neuron of) the output layer is computed.
Backward pass: in this step the network error is
used for updating the weights. Starting at the
output layer, the error is propagated backwards
through the network, layer by layer. This is done
by recursively computing the local gradient of
each neuron.
 APPLICATIONS
Neural networks has many applications such as,
Pattern recognization.
In airplanes neural network used as a basic
autopilot.
Inside a factory, you could use a neural network for
quality control (Eg :detergent companies).
A quick automated way of identifying any
transactions in banks.
forecast the stock market or the weather.
operate radar scanning systems that automatically
identify enemy aircraft or ships.
 APPLICATIONS
Use cellphone apps that recognize your
handwriting on a touchscreen.
Voice recognition software also use neural
networks.
Some of the email programs that automatically
differentiate between genuine emails and spam.
Help doctors to diagnose complex diseases on the
basis of their symptoms.
 ADVANTAGES

Training large amount of data sets.

The output performance will depend upon the

trained parameters and the data set relevant to the
training.

Adaptive learning

Self-Organisation

Real Time Operation

 FUTURE SCOPE
Common usage of self-driving cars.

Handwritten documents to be automatically

transformed into formatted word processing
documents.

Self diagnosis of medical problems using neural

networks.
 CONCLUSION
The computing world has a lot to gain from neural
networks.

Their ability to learn by example makes them very

flexible and powerful.

There is no need to understand the internal

mechanisms of that task.
THANK YOU