Aditi Report

8/6/2019 Aditi Report

1/3

1. INTRODUCTION

1.1 ARTIFICIAL NEURAL NETWORKS

The term neural network was traditionally used to refer to a network or circuit of

biological neurons. The modern usage of the term often refers to artificial neural

networks, which are composed ofartificial neurons or nodes. An artificial neural network

(ANN), usually called neural network(NN), is a mathematical model or computational

model that is inspired by the structure and/or functional aspects of biological neural

networks (BNN).

A neural network consists of an interconnected group of artificial neurons. It

processes information using a connectionist approach to computation. In most cases an

ANN is an adaptive system that changes its structure based on external or internal

information that flows through the network during the learning phase.

Modern neural networks are non-linearstatistical data modelling tools. They are

generally used to model complex relationships between inputs and outputs or to find

patterns in data. ANNs are non-linear mapping structures based on the function of the

human brain. They are powerful tools for modelling, especially when the underlying data

relationship is unknown. ANNs can identify and correlate patterns between input data

sets and corresponding target values. After training, ANNs can be used to predict the

outcome of new independent input data. ANNs imitate the learning process of the human

brain and can process problems involving non-linear and complex data even if the data

are imprecise and noisy.

ANNs have a great capacity in predictive modelling, i.e., all the characters

describing the unknown situation can be presented to the trained ANNs, and then

prediction of systems is guaranteed.

An ANN is a computational structure that is inspired by observed process in

natural networks of biological neurons in the brain. It consists of simple computational

units called neurons, which are highly interconnected. ANNs have become the focus of

much attention, largely because of their wide range of applicability and the ease with

which they can treat complicated problems. ANNs are parallel computational models

comprised of densely interconnected adaptive processing units. These networks are fine-

grained parallel implementations of non-linear static or dynamic systems.

1 | P a g e
http://en.wikipedia.org/wiki/Neuronhttp://en.wikipedia.org/wiki/Artificial_neural_networkhttp://en.wikipedia.org/wiki/Artificial_neural_networkhttp://en.wikipedia.org/wiki/Artificial_neuronhttp://en.wikipedia.org/wiki/Artificial_neuronhttp://en.wikipedia.org/wiki/Neural_networkhttp://en.wikipedia.org/wiki/Artificial_neuronhttp://en.wikipedia.org/wiki/Connectionismhttp://en.wikipedia.org/wiki/Computationhttp://en.wikipedia.org/wiki/Adaptive_systemhttp://en.wikipedia.org/wiki/Non-linearhttp://en.wikipedia.org/wiki/Statisticalhttp://en.wikipedia.org/wiki/Pattern_recognitionhttp://en.wikipedia.org/wiki/Pattern_recognitionhttp://en.wikipedia.org/wiki/Neuronhttp://en.wikipedia.org/wiki/Artificial_neural_networkhttp://en.wikipedia.org/wiki/Artificial_neural_networkhttp://en.wikipedia.org/wiki/Artificial_neuronhttp://en.wikipedia.org/wiki/Neural_networkhttp://en.wikipedia.org/wiki/Artificial_neuronhttp://en.wikipedia.org/wiki/Connectionismhttp://en.wikipedia.org/wiki/Computationhttp://en.wikipedia.org/wiki/Adaptive_systemhttp://en.wikipedia.org/wiki/Non-linearhttp://en.wikipedia.org/wiki/Statisticalhttp://en.wikipedia.org/wiki/Pattern_recognitionhttp://en.wikipedia.org/wiki/Pattern_recognition


2/3

Figure 1.1 Information Processing

A vey important feature of these networks is their adaptive nature, where "learning by

example" replaces "programming" in solving problems. This feature makes such

computational models very appealing in application domains where training data is

readily available. ANNs are now being increasingly recognised in the area of

classification and prediction, where statistical techniques have traditionally been

employed. ANNs are "neural" in the sense that they may have been inspired by

neuroscience but not necessarily because they are faithful models of biological neural or

cognitive phenomena. In fact, majority of the networks are more closely related

traditional mathematical and/or statistical models.

1.2 NEURAL NETS

The term Neural Net refers to both the biological and artificial variants, although typically

the term is used to refer to artificial systems only. Mathematically, neural nets are

nonlinear. Each layer represents a non-linear combination of non-linear functions from

the previous layer. Each neuron is a multiple-input, multiple-output (MIMO) system that

receives signals from the inputs, produces a resultant signal, and transmits that signal to

all outputs. Practically, neurons in an ANN are arranged into layers. The first layer that

interacts with the environment to receive input is known as the input layer. The final layer

2 | P a g e


3/3

that interacts with the output to present the processed data is known as the output layer.

Layers between the input and the output layer that do not have any interaction with the

environment are known as hidden layers. Increasing the complexity of an ANN, and thus

its computational capacity, requires the addition of more hidden layers, and more neurons

per layer.

Biological neurons are connected in very complicated networks. Some regions of

the human brain such as the cerebellum are composed of very regular patterns of neurons.

Other regions of the brain, such as the cerebrum have less regular arrangements. A typical

biological neural system has millions or billions of cells, each with thousands of

interconnections with other neurons. Current artificial systems cannot achieve this level

of complexity, and so cannot be used to reproduce the behaviour of biological systems

exactly.

1.3 NEED FOR NEURAL NETWORKS!

Neural networks, with their remarkable ability to derive meaning from complicated or

imprecise data, can be used to extract patterns 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. This

expert can then be used to provide projections given new situations of interest and answermany questions. Other features include:

1. Adaptive learning

An ability to learn how to do tasks based on the data given for training or initial

experience.

2. Self-Organisation

An ANN can create its own organisation or representation of the information it

receives during learning time.

3. Real Time Operation

ANN computations may be carried out in parallel, and special hardware devices are

being designed and manufactured which take advantage of this capability.

4. Fault Tolerance via Redundant Information Coding

Partial destruction of a network leads to the corresponding degradation of

performance. However, some network capabilities may be retained even with major

network damage.

3 | P a g e

Documents

Aditi Report