ARTIFICIAL NEURAL
NETWORK
What is Artificial Neural Network?
The term "Artificial Neural Network" is derived from
Biological neural networks that develop the structure
of a human brain. Similar to the human brain that has
neurons interconnected to one another, artificial
neural networks also have neurons that are
interconnected to one another in various layers of the
networks. These neurons are known as nodes.
The three main types of layers in a typical ANN
are:
Input Layer: This layer receives the initial data or input
features. Each neuron in this layer represents a feature of
the input data.
Hidden Layers: These layers perform computations on the
input data. Each neuron in a hidden layer receives inputs
from the previous layer, applies a transformation (usually
through an activation function), and passes the result to the
next layer.
Output Layer: This layer produces the final output of the
network. The number of neurons in the output layer
depends on the type of problem the ANN is solving. For
example, for binary classification, there may be one neuron
for each class, while for regression, there might be just one
neuron.
Neural Network Topologies:
• Feedforward neural network: The feedforward
neural network was the first and arguably simplest
type of artificial neural network devised. In this
network, the information moves in only one
direction, forward, from the input nodes, through
the hidden nodes (if any) and to the output nodes
There are no cycles or loops in the network. The data
processing can extend over multiple (layers of) units, but no
feedback connections are present, that is, connections
extending from outputs of units to inputs of units in the
same layer or previous layers.
Recurrent network: Recurrent neural networks that do
contain feedback connections. Contrary to feedforward
networks, recurrent neural networks (RNs) are models
with bi-directional data flow. While a feedforward network
propagates data linearly from input to output, RNs also
propagate data from later processing stages to earlier
stages.
Training Of Artificial Neural Networks:
A neural network has to be configured such that
the application of a set of inputs produces (either
'direct' or via a relaxation process) the desired set of
outputs. Various methods to set the strengths of the
connections exist. One way is to set the weights
explicitly, using a priori knowledge. Another way is
to 'train' the neural network by feeding it
teaching patterns and letting it change its weights
according to some learning rule
We can categorize the learning situations as follows:
Supervised learning or Associative learning
in which the network is trained by providing it
with input and matching output patterns. These
input-output pairs can be provided by an
external teacher, or by the system which
contains the neural network (self-supervised).
Unsupervised learning or Self-organization in
which an (output) unit is trained to respond to
clusters of pattern within the input. In this
paradigm the system is supposed to discover
statistically salient features of the input
population. Unlike the supervised learning
paradigm, there is no a priori set of categories
into which the patterns are to be classified;
rather the system must develop its own
representation of the input stimuli.
Reinforcement Learning This type of
learning may be considered as an intermediate
form of the above two types of learning. Here
the learning machine does some action on the
environment and gets a feedback response
from the environment. The learning system
grades its action good (rewarding) or bad
(punishable) based on the environmental
response and accordingly adjusts its
parameters.
Some applications of ANNs include:
• Text Classification and Categorization
This is vital part of several applications like web searching,
information filtering, language identification, readibility
assessment, as well as sentiment analysis. Artificial neural
networks are widely used for these tasks.
• Named Entity Recognition (NER)
Named entity recognition involves focuses on categorizing
named entities predefined classes like persons,
organizations, locations, dates, times, etc. The most
effective and powerful named entity recognition systems
make use of artificial neural networks.
• Part-of-Speech Tagging
Part-of-speech tagging is used for parsing, text-to-speech
conversion, information extraction and many other
applications. The process is about tagging words as
adjectives, verbs, nouns, adverbs, pronouns, etc.
• Machine Translation
Machine translation is widely used around the world,
however, it still has certain limitations and there are certain
domains in which the quality of the translations is rather
substandard. To improve the quality of machine
translations, researchers are attempting to use neural
• Semantic Parsing and Question Answering
Such systems automate the answering of various types of
questions (this includes definition questions, biographical
questions, multilingual questions, and many other kinds of
questions) that are asked to the system in natural language.
Using artificial neural networks, it is possible to create high-
performance question answering systems.
• Paraphrase Detection
This essentially involves figuring out whether two sentences
mean the same thing. This is particularly important in
question answering systems because there are several
ways in which your users could ask the very same question.
• Speech Recognition
Artificial neural networks are used rather extensively in
speech recognition. It involves making use of natural
language processing to convert voice data into a machine-
readable format.
• Language Generation & Multi-document Summarization
Natural language generation (NLG) can be used for various reports.
Some of them include writing reports, generating texts based on the
data that the system analyzed, drafting summaries of electronic
medical records and generating textual weather forecasts based on
weather data.
• 9. Character Recognition
Character recognition is applied to receipts, invoices, cheques, legal
documents, etc. By using artificial neural networks, character
recognition can even be performed on hand-written characters with
an accuracy of around 85%.
• Spell Checking
This is widely used in text editors to inform users if their text
contains spelling errors. Several spell-checking tools now
make use of artificial neural networks.
advantages of Artificial Neural Networks
• Fault tolerance
Even if one or more cells of the ANN get corrupted, the
generation of outputs will not be affected.
• Parallel processing
Artificial neural networks have the ability to perform multiple
functions simultaneously.
• Training
They are able to bear long training times, can learn from
events and make decisions based on similar events.
• Gradual corruption
An artificial neural network does degrade and slow down
over time. However, the ANN does not get corroded
instantly.
• Speed
ANNs are put to use in cases where a quick evaluation of
the learned target function is necessary.
Disadvantages of Artificial Neural Networks
• Lack of transparency
The functioning of the ANNs is not clear, and the solutions
reached do not come with explanations as to how or why
they were reached.
• Difficulties in introducing problems to artificial
neural networks
Artificial neural networks work with numerical information.
Therefore, before you introduce your problem to the artificial
neural network, you need to convert it into numerical
values.
• No rules for structures
Artificial neural networks that no rules that govern their
structures. You can reach an appropriate network structure
through trial & error and experience.
