Seminar on Artificial Neural Network

8/8/2019 Seminar on Artificial Neural Network

http://slidepdf.com/reader/full/seminar-on-artificial-neural-network 1/17

Artificial neural network



What is a Neural Network?

An Artificial Neural Network (ANN) is an information

processing paradigm that is inspired by the way biological

nervous systems, such as the brain, process information. The

key element of this paradigm is the novel structure of the

information processing system. It is composed of a largenumber of highly interconnected processing elements

(neurones) working in unison to solve specific problems.

ANNs, like people, learn by example. An ANN is configured

for a specific application, such as pattern recognition or dataclassification, through a learning process.



Historical background

Neural network simulations appear to be a recent development. However,

this field was established before the advent of computers, and has survived

at least one major setback and several eras.

Following an initial period of enthusiasm, the field survived a period of

frustration and disrepute. During this period when funding and professional

support was minimal, important advances were made by relatively fewresearchers.

The first artificial neuron was produced in 1943 by the neurophysiologist

Warren McCulloch and the logician Walter Pits. But the technology

available at that time did not allow them to do too much.



From Human Neurones to Artificial Neurones

We conduct these neural networks by first trying to deducethe essential features of neurones and their

interconnections. We then typically program a computer to

simulate these features. However because our knowledge of

neurones is incomplete and our computing power is limited,

our models are necessarily gross idealisations of real

networks of neurones.



Why use neural networks?

Adaptive learning: An ability to learn how to do tasks basedon the data given for training or initial experience.

Self-Organisation: it can create its own organisation or

representation of the information it receives during learning

time.

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.

Fault Tolerance: Partial destruction of a network leads to the

corresponding degradation of performance. However, somenetwork capabilities may be retained even with major network

damage.



Neural networks versus conventional computers

Neural networks take a different approach to problem solving than that of conventional computers.

Conventional computers use an algorithmic approach

Neural networks process information in a similar way the human braindoes. They need not be programmed to perform a specific task.

conventional computers use a cognitive approach to problem solving

Neural networks and conventional algorithmic computers are not in

competition but complement each other.



Feed-forward networks Feedback networks



Feed-forward networks

Feed-forward ANNs allow signals to travel one way only from input

to output.

There is no feedback (loops) i.e. the output of any layer does not

affect that same layer.

They are extensively used in pattern recognition.

Feedback networks

These have signals travelling in both directions by introducing loops in

the network. Feedback networks are dynamic; their 'state' is changing continuously

until they reach an equilibrium point. They remain at the equilibrium point

until the input changes and a new equilibrium needs to be found



The activity of the input units

represents the raw information that is

fed into the network.

The activity of each hidden unit isdetermined by the activities of the input

units and the weights on the connections

between the input and the hidden units.

The behavior of the output unitsdepends on the activity of the hidden

units and the weights between the

hidden and output units.



Training of artificial neural networks

Supervised learning or Associative learning in which the network is trained

by providing it with input and matching output patterns.

Unsupervised learning or Self-organisation 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.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 andaccordingly adjusts its parameters. Generally, parameter adjustment is

continued until an equilibrium state occurs, following which there will be no

more changes in its parameters.



Using a Neural Network

The type of problem amenable to solution by a neural network is defined by the

way they work and the way they are trained. They can be used where we havesome known information, and would like to infer some unknown information.

Some examples are:

Stock market prediction

Credit assignment.

Control.

The relationship between known input and unknown output may be noisy

neural networks learn the input/output relationship through training.

If the network is properly trained, it has then learned to model the (unknown)function that relates the input variables to the output variables, and can

subsequently be used to make predictions where the output is not known.



Gathering Data for Neural Networks

Choose variables that you believe may be influential.

Numeric and nominal variables can be handled. Convert other

variables to one of these forms, or discard.

Hundreds or thousands of cases are required; the more

variables, the more cases.

Cases with missing values can be used, if necessary - check

your data. If you have sufficient data, discard cases with

missing values.

If the volume of the data available is small, consider usingensembles and resempling of data.



Data Selection

The training, verification and test data must be representative of the

underlying model. If training data is not representative, then the model's worthis at best compromised. At worst, it may be useless. It is worth spelling out

the kind of problems which can corrupt a training set:

The future is not the past. Training data is typically historical. If

circumstances have changed, relationships which held in the past may nolonger hold.

All eventualities must be covered. A neural network can only learn from

cases that are present.

A network learns the easiest features it can.

Unbalanced data sets. Since a network minimizes an overall error, the

proportion of types of data in the set is critical. Often, the best approach is to

ensure even representation of different cases, then to interpret the network's

decisions accordingly.



Applications of neural networks

Neural Networks in Practice

Since neural networks are best at identifying patterns or trends in data, they

are well suited for prediction or forecasting needs including:

sales forecasting

industrial process controlcustomer research

data validation

risk management

target marketing



Neural networks in medicine:

At the moment, the research is mostly on modelling parts of the human

body and recognising diseases from various scans.

Modelling and iagnosing the ardiovascular ystem

Instant Physician.

Neural Networks in business

neural networks can be used for business purposes, including resourceallocation and scheduling. There is also a strong potential for using

neural networks for database mining, that is, searching for patterns

implicit within the explicitly stored information in databases.

MarketingThe Airline Marketing Tactician(AMT) is a computer system made of

various intelligent technologies including expert systems. A feed forward

neural network is integrated with the AMT and trained to assist the

marketing control of airline seat allocations.

Seminar on Artificial Neural Network

Documents

Transcript of Seminar on Artificial Neural Network