See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/319903816

AN INTRODUCTION TO ARTIFICIAL NEURAL NETWORK

Article  in  International Journal Of Advance Research And Innovative Ideas In Education · September 2016

CITATIONS READS
15 32,361

1 author:

Kuldeep Shiruru
Jain University
13 PUBLICATIONS   20 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Smart grids, Power and Advanced Control Engineering View project

Short Term Load Forecasting View project

All content following this page was uploaded by Kuldeep Shiruru on 19 September 2017.

The user has requested enhancement of the downloaded file.

Vol-1 Issue-5 2016 IJARIIE-ISSN (O)-2395-4396

AN INTRODUCTION TO ARTIFICIAL
NEURAL NETWORK
Harsh Kukreja1, Bharath N1, Siddesh C S1, Kuldeep S2

UG Student, 2 Assistant Professor,

1
1, 2
Department of Electrical & Electronics Engineering, School of Engineering & Technology, Jain
University, Bangalore

ABSTRACT
Artificial Neural Network (ANN) is gaining prominence in various applications like pattern recognition, weather
prediction, handwriting recognition, face recognition, autopilot, robotics, etc. In electrical engineering, ANN is being
extensively researched in load forecasting, processing substation alarms and predicting weather for solar radiation and
wind farms. With more focus on smart grids, ANN has an important role. ANN belongs to the family of Artificial
Intelligence along with Fuzzy Logic, Expert Systems, Support Vector Machines. This paper gives an introduction into
ANN and the way it is used.

Keywords: - Artificial neural network, ANN, back propagation algorithm, neuron, weights

1. INTRODUCTION

In its simplest form, an artificial neural network (ANN) is an imitation of the human brain. A natural brain has the ability to
learn new things, adapt to new and changing environment. The brain has the most amazing capability to analyze
incomplete and unclear, fuzzy information, and make its own judgment out of it. For example, we can read other’s
handwriting though the way they write may be completely different from the way we write. A child can identify that the
shape of a ball and orange are both a circle. Even a few days old baby has the ability to recognize its mother from the touch,
voice and smell. We can identify a known person even from a blurry photograph.

Brain is a highly complex organ that controls the entire body. The brain of even the most primitive animal has more
capability than the most advanced computer. Its function is not just controlling the physical parts of the body, but also of
more complex activities like thinking, visualizing, dreaming, imagining, learning etc, activities that cannot be described in
physical terms. An artificial thinking machine is still beyond the capacity of the most advanced supercomputers.

2. BRAIN NEURON
Brain is made of cells called neurons. Interconnection of such cells (neurons) makes up the neural network or the brain.
There are about 1011 neurons in the human brain and about 10000 connections with each other. ANN is an imitation of
the natural neural network where the artificial neurons are connected in a similar fashion as the brain network.

A biological neuron is made up of cell body, axon and dendrite. Dendrite receives electro-chemical signals from other
neurons into the cell body. Cell body, called Soma contains nucleus and other chemical structures required to support the
cell. Axon carries the signal from the neuron to other neurons. Connection between dendrites of two neurons, or neuron
to muscle cells is called synapse [1].

C-1399 www.ijariie.com 27
Vol-1 Issue-5 2016 IJARIIE-ISSN (O)-2395-4396

Fig 1: Brain neuron [2]

The neuron receives signals from other neurons through dendrites. When the strength of the signal exceeds a
certain threshold, this neuron triggers its own signal to be passed on to the next neuron via the axon using
synapses. The signal sent to other neurons through synapses trigger them, and this process continues [2]. A huge
number of such neurons work simultaneously. The brain has the capacity to store large amount of data.

3. ARTIFICIAL NEURON
An artificial neural network consists of processing units called neurons. An artificial neuron tries to replicate the
structure and behavior of the natural neuron. A neuron consists of inputs (dendrites), and one output (synapse via axon).
The neuron has a function that determines the activation of the neuron.

Fig 2: Model of an artificial neuron [3]

x1...xn are the inputs to the neuron. A bias is also added to the neuron along with inputs. Usually bias value is
initialised to 1. W0...Wn are the weights. A weight is the connection to the signal. Product of weight and input gives
the strength of the signal. A neuron receives multiple inputs from different sources, and has a single output.

There are various functions used for activation. One of the most commonly used activation function is the sigmoid
function, given by

where

C-1399 www.ijariie.com 28
Vol-1 Issue-5 2016 IJARIIE-ISSN (O)-2395-4396

Fig 3: Sigmoid function [5]

The other functions that are used are Step function, Linear function, Ramp function, Hyperbolic tangent function.
Hyperbolic tangent (tanh) function is similar in shape to sigmoid, but its limits are from -1 to +1, unlike sigmoid
which is from 0 to 1.

The sum is the weighted sum of the inputs multiplied by the weights between one layer and the next. The
activation function used is a sigmoid function, which is a continuous and differentiable approximation of a step
function [2]. An interconnection of such individual neurons forms the neural network.

The ANN architecture comprises of:

a. input layer: Receives the input values
b. hidden layer(s): A set of neurons between input and output layers. There can be single or multiple layers
c. output layer: Usually it has one neuron, and its output ranges between 0 and 1, that is, greater than 0 and less
than 1. But multiple outputs can also be present [4].

Fig 4: Neural network architecture [3]

The processing ability is stored in inter-unit connection strengths, called weights [3]. Input strength depends on the
weight value. Weight value can be positive, negative or zero. Negative weight means that the signal is reduced or
inhibited. Zero weight means that there is no connection between the two neurons. The weights are adjusted to
obtain the required output. There are algorithms to adjust the weights of ANN to get the required output. This
process of adjusting weights is called learning or training [2].

4. ANN TRAINING PROCESS

Categories of ANN are based on supervised and unsupervised learning methods. The simplest form of ANN architecture
is the Perception, which consists of one neuron with two inputs and one output. The activation function used is step
function or ramp function. Perceptions are used for classification of data into two separate classes. For more complex
applications, multilayer perceptions (MLP) are used, which contain one input layer, one output layer, and one or more
hidden layers as given in Fig 2.

Back propagation algorithm is the most commonly used method in training the neural network. Here the difference in
targeted output, and the output obtained, is propagated back to the layers and the weights adjusted. A back propagation

C-1399 www.ijariie.com 29
 Vol-1 Issue-5 2016 IJARIIE-ISSN (O)-2395-4396

neural network (BPNN) uses a supervised learning method and feed-forward architecture. It is one of the most
frequently utilized neural network techniques for classification and prediction.

In BP algorithm, the outputs of hidden layers are propagated to the output layer where the output is calculated. This
output is compared with the desired output for the given input. Based on this difference, the error is propagated back
from the output layer to hidden layer, and from hidden layer to input layer. As the flow moves back, it changes the
weights between the neurons. This cycle of going forward from input and output, and from output to input is called an
epoch. A neural network is first given a set of known input data and asked to obtain a known output. This is called
training the network. The network undergoes many such epochs till the error (difference between actual output and
desired output) is within a certain tolerance). Now the network is said to be trained. This process of training sets the
weights between all the neurons in all the layers. The weights so obtained from a trained network are used in calculating
the response of the network to an unknown data.

5. STRENGTHS AND LIMITATIONS OF ANN

ANN is different from a normal computer program in many ways. Some of its features are: [6]
a. Adaptive learning: ANN replicates human brain in the way it learns how to do tasks while learning. A normal
program cannot adapt to other types of inputs
b. Self organization: ANN can create its own organization while learning. A normal program is fixed for its task
and will not do anything other than what it is intended to do
c. Parallel operation: ANN works in parallel like a human brain. This is dissimilar to a computer program which
works serially.
d. Fault tolerance: One of the most interesting properties of neural networks is their ability to work even on the
basis of incomplete, noisy, and fuzzy data. A normal program cannot handle incomplete, unclear data and will stop
working once it encounters the smallest wrong data.
e. In comparison with human brain, ANN is quite fast, as brain processing time is slower
f. In comparison with normal program, the method in which ANN calculates output is not clear. The time taken
keeps changing with different sets of inputs, though they are similar.
g. ANN can be used for data classification, pattern recognition, and in applications where data is unclear
h. ANN cannot be used when the nature of input and output is exactly known, and what needs to be done is clearly
known.

6. EFERENCES
[1]. Emil M Petriu, Professor, University of Ottawa, "Neural Networks: Basics"
[2]. Carlos Gershenson, "Artificial Neural Networks for Beginners", arxiv.org
[3]. Kuldeep S, Dr. Anitha G S, "Neural Network Approach for Processing Substation Alarms", International
Journals of Power Electronics Controllers and Converters
[4]. M. Abdelrahman "Artificial neural networks based steady state security analysis of power systems", Thirty-
Sixth Southeastern Symposium on System Theory 2004 Proceedings, 2004
[5]. K Y Lee, Y T Cha, J H Park, "Short Term Load Forecasting Using an Artificial Neural Network",
Transactions on Power Systems, Vol 1, No 7
[6]. O.S. Eluyode, Dipo Theophilus Akomolafe, "Comparative Study of Biological and Artificial Neural
Networks", European Journal of Applied Engineering and Scientific Research, 2013, 2(1):36-46

C-1399 www.ijariie.com 30

View publication stats