Demystifying Neural

Networks
Neelam Batra
Agenda :

• What is Neural Networks ?

• Working of Artificial Neuron
• How Neural Network works ?
• Parameters and Hyperparameters of Neural Network
• Different Types of Neural Network
• Applications of Neural Network
Artificial Intelligence vs Machine Learning vs Neural Networks

Artificial Intelligence (AI) is a

Artificial Intelligence term used for machines that
interpret the data, learn from
it and use it to do the tasks
usually performed by the
Machine Learning humans.
Machine Learning is a branch
A
of Artificial Intelligence that
focuses on training the
machines by pattern
Neural
recognition or examples
Networks
instead of specifically
programming them how to
solve the task.
Neural Networks is a subset of
Machine Learning and is a
highly advanced application of
Machine learning. It uses
networks of multiple layers for
training the machines. Due to
multiple layers being used it’s
also called Deep Learning.
 What is Neural Networks ?
Neural Network is a Machine Learning approach inspired by the way in which brain performs a particular
learning task

Dendrites
These receive information or signals from other
neurons that get connected to it.
Cell Body
Information processing happens in a cell body.
These take in all the information coming from the
different dendrites and process that information..
Axon
It sends the output signal to another neuron for
the flow of information. Here, each of the flanges
connects to the dendrite or the hairs on the next
one. .
 What is Neural Networks (Cont.)?

Neural networks, is also called

artificial neural networks
(ANN).
Artificial Neural Networks, is a
collection of a large
number of simple devices
called artificial neurons.
The network learns
to inhibit or amplify the
input signals in order to
This layer delivers
the final result perform a task, such as
recognising a cat, speaking
Picks up input
signals and passes a word, identifying a tree
them to next layer Does all kinds of etc.
calculations and feature
extraction
Working of Artificial Neuron

A weight represent the
strength of the connection
between units.
Activation function is used to
measure the weighted sum
produced by a neuron and to
decide whether this neuron
should be “fired/activated” or
not.
Bias allows you to shift the
activation function by adding a
constant (i.e. the bias) to the
input
Types of Activation Functions

Sigmoid Function
The sigmoid function is used when the
model is predicting probability

Threshold Function
The threshold function is used when you
don’t want to worry about the
uncertainty in the middle.

ReLU (rectified linear unit) Function

The ReLU (rectified linear unit) function
gives the value but says if it’s over 1,
then it will just be 1, and if it’s less
than 0, it will just be 0. The ReLU
function is most used these days. 

Hyperbolic Tangent Function

The hyperbolic tangent function is
similar to the sigmoid function but has a
range of -1 to 1.
Different Types of Neural Network

• Feed-forward Neural Network

This is the simplest form of ANN(Artificial Neural Network), data travels only in one
direction (input to output). This is the example we just looked at. Almost all vision and
speech recognition applications use some form of this type of neural network.

• Recurrent Neural Network

In this type, the hidden layer saves its output to be used for future prediction. The
output becomes part of its new input. Applications include text-to-speech conversion. 

• Convolution Neural Network

In this type, the input features are taken in batches—as if they pass through a filter.
This allows the network to remember an image in parts. Applications include signal and
image processing, such as facial recognition.
Applications of Neural Network

• Handwriting Recognition
• Stock Exchange Prediction
• Image Classification
• Image Compression
• Text Translation
• Medical Diagnosis
• Voice Recognition
• Face Recognition
• Signature Verification
• Control Robots
• Gesture Recognition
• And a lot more
References

 https://www.simplilearn.com/tutorials/deep-learning-tutorial/neural-network?sour
ce=sl_frs_nav_playlist_video_clicked
 https://www.youtube.com/watch?v=aircAruvnKk&list=PLZHQObOWTQDNU6R1_6700
0Dx_ZCJB-3pi