Neural Networks

Team Members
▪ SRINIVASH.R
▪ SRIRAM.S
▪ SANJAY.P
▪ SURAESH KRISHNAA.K.S

Guided By,
Ms. SRIMATHI.

NEURAL NETWORKS 7-Dec-18 2

Contents:
▪ What is a Neural Network?
▪ Why use Neural Networks?
▪ History and evolutions
▪ An engineering approach
▪ Architecture of Neural Networks
▪ Image recognition by CNN
▪ Neural networks in medicine
▪ Applications of neural networks
▪ Conclusion

NEURAL NETWORKS 7-Dec-18 3

What is Neural Network?

▪ An Artificial Neural Network (ANN) is an information processing

paradigm that is inspired by the way biological nervous systems, such
as the brain, process information.
▪ It consists of large number of highly interconnected neurons in it to
carry information.
▪ ANNs learn by example which we given as the data's.
▪ Ex:Pattern recognition or data classification, through a learning
process.

NEURAL NETWORKS 7-Dec-18 4

▪ Neural Network: A computational model that works in a similar way to
the neurons in the human brain.
▪ Each neuron takes an input, performs some operations then passes the
output to the following neuron.

NEURAL NETWORKS 7-Dec-18 5

Why use Neural Network?

▪ Neural networks, with their remarkable ability to derive and detect

trends that are too complex to be noticed by either humans or other
computer techniques.
▪ A trained neural network can be thought of as an "expert" in the
category of information it has been given to analyse.
▪ Other advantages include:

NEURAL NETWORKS 7-Dec-18 6

▪ Adaptive learning: An ability to learn how to do tasks based on the
data given for training or initial experience.
▪ Self-Organisation: An ANN can create its own organisation or
representation of the information it receives during learning time.

NEURAL NETWORKS 7-Dec-18 7

History and evolutions

▪ Neural network simulations appear to be a recent development.

However, this field was established before the advent of computers,
and has survived at least one major setback and several eras.
▪ In 1943, neurophysiologist Warren McCulloch and mathematician
Walter Pitts wrote a paper on how neurons might work.

NEURAL NETWORKS 7-Dec-18 8

▪ As computers became more advanced in the 1950's, it was finally
possible to simulate a hypothetical neural network. The first step
towards this was made by Nathanial Rochester from the IBM
research laboratories. Unfortunately for him, the first attempt to do
so failed.
▪ In 1959, Bernard Widrow and Marcian Hoff of Stanford developed
models called "ADALINE" and "MADALINE." MADALINE was the first
neural network applied to a real world problem, using an adaptive
filter that eliminates echoes on phone lines.
▪ The first multi-layered network was developed in 1975, an
unsupervised network.

NEURAL NETWORKS 7-Dec-18 9

An engineering approach:

SIMPLE 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. In the training mode, the neuron can be trained to fire
(or not), for particular input patterns.
▪ In the using mode, when a taught input pattern is detected at the
input, its associated output becomes the current output.
▪ If the input pattern does not belong in the taught list of input
patterns, the firing rule is used to determine whether to fire or not.

NEURAL NETWORKS 7-Dec-18 10

Artificial Neuron:

NEURAL NETWORKS 7-Dec-18 11

TYPES OF NEURONS:

▪ Feed forward Neural Network – Artificial Neuron

▪ Radial basis function Neural Network
▪ Kohonen Self Organizing Neural Network
▪ Recurrent Neural Network(RNN) – Long Short Term1Memory
▪ Convolutional Neural Network
▪ Modular Neural Network

NEURAL NETWORKS 7-Dec-18 12

Feed forward Neural Network

▪ This neural network is one of the simplest form of ANN, where the
data or the input travels in one direction. The data passes through
the input nodes and exit on the output nodes.

NEURAL NETWORKS 7-Dec-18 13

Architecture of Neural Networks

NETWORK LAYER:
▪ The commonest type of artificial neural network consists of three
groups, or layers of units:
▪ a layer of "input" units is connected to a layer of "hidden" units,
which is connected to a layer of "output" units.

NEURAL NETWORKS 7-Dec-18 14

Image recognition by CNN

▪ One of the most popular techniques used in improving the accuracy

of image classification is Convolutional Neural Networks (CNNs for
short).
▪ Instead of feeding the entire image as an array of numbers, the
image is broken up into a number of tiles, the machine then tries to
predict what each tile is.
▪ Finally, the computer tries to predict what’s in the picture based on
the prediction of all the tiles.
▪ This allows the computer to parallelize the operations and detect the
object regardless of where it is located in the image.

NEURAL NETWORKS 7-Dec-18 15

Convolutional layer

▪ Convolution means twisted or difficult to follow .

▪ The convolutional layer is the core building block of a CNN.
▪ The hidden layers of a CNN typically consist of convolutional layers.
▪ Convolutional layers apply a convolution operation to the input,
passing the result to the next layer.

NEURAL NETWORKS 7-Dec-18 16

NEURAL NETWORKS 7-Dec-18 17
NEURAL NETWORKS 7-Dec-18 18
INPUT AND OUTPUT SET:
▪ When a computer sees an image (takes an image as input), it will see
an array of pixel values.

▪ Ex:28*28 Pixels.
PRE-PROCEESING:
▪ Crops parts of the image
▪ Flip image horizontally
▪ Adjust hue, contrast and saturation

NEURAL NETWORKS 7-Dec-18 19

Pre-processing

NEURAL NETWORKS 7-Dec-18 20

Splitting our
Dataset
NEURAL NETWORKS 7-Dec-18 21
NEURAL NETWORKS 7-Dec-18 22
Results

▪ The given datasets are recognized by the pre-processing and

splitting process;
▪ And the output is shown to us what image is given in the input .

NEURAL NETWORKS 7-Dec-18 23

NEURAL NETWORKS 7-Dec-18 24
Neural networks in medicine

▪ Artificial Neural Networks (ANN) are currently a 'hot' research area in

medicine
▪ (e.g. cardiograms, CAT scans, ultrasonic scans, etc.).
▪ Neural networks are ideal in recognising diseases using scans since
there is no need to provide a specific algorithm on how to identify the
disease.
▪ Neural networks learn by example so the details of how to recognise
the disease are not needed. What is needed is a set of examples that
are representative of all the variations of the disease.

NEURAL NETWORKS 7-Dec-18 25

Applications of neural networks

▪ Neural networks have broad applicability to real world business

problems. In fact, they have already been successfully applied in
many industries.
▪ Sales Forecasting
▪ Industrial Process Control
▪ Customer Research
▪ Data Validation
▪ Risk Management
▪ Target Marketing

NEURAL NETWORKS 7-Dec-18 26

 ▪ ANN are also used in the following specific paradigms:
▪ Recognition of speakers in communications;

▪ Hand-written word recognition and

▪ Facial recognition.

NEURAL NETWORKS 7-Dec-18 27

NEURAL NETWORKS 7-Dec-18 28
NEURAL NETWORKS 7-Dec-18 29
Conclusion

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

▪ Their ability to learn by example makes them very flexible and
powerful
▪ They are also very well suited for real time systems
▪ Neural networks also contribute to other areas of research such as
neurology and psychology
▪ Finally, I would like to state that even though neural networks have a
huge potential we will only get the best of them. when they are
integrated with computing, AI, fuzzy logic and related subjects.

NEURAL NETWORKS 7-Dec-18 30

NEURAL NETWORKS 7-Dec-18 31
NEURAL NETWORKS 7-Dec-18 32