See discussions, stats, and author profiles for this publication at:

https://www.researchgate.net/publication/319903816

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

September 2017.
The user has requested enhancement of the downloaded file.

Artificial Neural Network 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.
ANN and the way it is used.

INTRODUCTION

In its simplest form, an artificial neural network 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.

BRAIN NEURON

Brain is made of cells called neurons. Interconnection of such cells 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 .

Fig 1: Brain neuron

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 . A huge number of such neurons work
simultaneously. The brain has the capacity to store large amount of data.

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 , and one output .
The neuron has a function that determines the activation of the neuron.

Fig 2: Model of an artificial neuron

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.

Fig 3: Sigmoid function

The other functions that are used are Step function, Linear function, Ramp
function, Hyperbolic tangent function.
Hyperbolic tangent 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 . 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: 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 .

Fig 4: Neural network architecture

The processing ability is stored in inter-unit connection strengths, called
weights . 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 .

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 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 neural network 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 . 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.
ANN is different from a normal computer program in many ways.

STRENGTHS AND LIMITATIONS OF ANN

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.
EFERENCES. Emil M Petriu, Professor, University of Ottawa, «Neural
Networks: Basics». Carlos Gershenson, «Artificial Neural Networks for
Beginners», arxiv.org. Kuldeep S, Dr. Anitha G S, «Neural Network
Approach for Processing Substation Alarms», International
Journals of Power Electronics Controllers and Converters. M. Abdelrahman
«Artificial neural networks based steady state security analysis of power
systems», ThirtySixth Southeastern Symposium on System Theory 2004
Proceedings, 2004. 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. O.S. Eluyode, Dipo Theophilus Akomolafe,
«Comparative Study of Biological and Artificial Neural
.