UNIT 8

INFORMATION PROCESSING

1
Unit-8 Information Processing  
Neural Network,
Processing,
Data Visualization and Reliability
Principles and Application domains.

2
 INTRODUCTION

Information processing is the change of information in

any manner detectable by an observer.

It is a process that describes everything that happens

(changes) in the universe.

Ex: Falling a rock(Change of position)

3
 WHAT IS NEURAL NETWORK
 An Artificial Neural Network (ANN) is an information processing
paradigm that is inspired by biological nervous systems.

 It is composed of a large number of highly interconnected

processing elements called neurons.

 An ANN is configured for a specific application, such as pattern

recognition or data classification.
 WHY USE NEURAL NETWORKS

 ability to derive meaning from complicated or imprecise data.

 extract patterns and detect trends that are too complex to be noticed by
either humans or other computer techniques.

 Adaptive learning

 Real Time Operation

 NEURAL NETWORKS V/S CONVENTIONAL COMPUTERS

  Conventional computers use an algorithmic approach, but

neural networks works similar to human brain and learns by
example.
 A SIMPLE NEURON

 Takes the Inputs .

 Calculate the summation of the Inputs .
 Compare it with the threshold being set during the learning
stage.
Definitions of a Neural Network:
A neural network is a system composed of many simple processing

elements operating in parallel whose function is determined by network

structure, connection strengths, and the processing performed at

computing elements or nodes.

8
A neural network is a massively parallel distributed processor that has a
natural tendency for storing experiential knowledge and making it
available for use.

It resembles the brain in two respects:

1. Knowledge is acquired by the network through a learning process.

2. Interneuron connection strengths known as synaptic weights are used

to store the knowledge.

9
 ANNs have been applied to an increasing number of real-world

problems of considerable complexity.

 Their most important advantage is in solving problems that are too

complex for conventional technologies -- problems that do not have

an algorithmic solution or for which an algorithmic solution is too

complex to be found.

10
 In general, because of their abstraction from the biological brain,

ANNs are well suited to problems that people are good at solving, but

for which computers are not.

 These problems include pattern recognition and forecasting.

11
 ARTIFICIAL NEURAL NETWORK MODEL

Desired
Hidden layers output
connections Neural
Input network Actual
output output
Including Com
connections pare
output layer (called
weights)
between
neuron

Input layer
 OTHER ADVANTAGES INCLUDE:

1. Adaptive learning: An ability to learn how to do tasks based on the data given
for training or initial experience.
2. Self-Organization: An ANN can create its own organization 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.
13
limits to Neural Networks

 The major issues of concern today are the scalability(=Scalability is the capability of a system,

network, or process to handle a growing amount of work, or its potential to be enlarged in order

to accommodate that growth.[1] For example, it can refer to the capability of a system to increase

its total output under an increased load when resources (typically hardware) are added.) problem,

testing, verification, and integration of neural network systems into the modern environment.

 Neural network programs sometimes become unstable when applied to larger problems.

 The defense, nuclear and space industries are concerned about the issue of testing and

verification.

 The mathematical theories used to guarantee the performance of an applied neural network are

still under development.

 The solution for the time being may be to train and test these intelligent systems much as we do

for humans.

14
Also there are some more practical problems like:
The operational problem encountered when attempting to simulate the
parallelism of neural networks.
Since the majority of neural networks are simulated on sequential
machines, giving rise to a very rapid increase in processing time
requirements as size of the problem expands.
 Solution: implement neural networks directly in hardware, but these
need a lot of development still.
Instability to explain any results that they obtain. Networks function as
"black boxes" whose rules of operation are completely unknown.
15
 Architecture of Neural Networks
 1. Feed-forward Networks
 Feed-forward ANNs (figure 1) 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. Feed-forward ANNs tend to be straight forward
networks that associate inputs with outputs.
 They are extensively used in pattern recognition.
 This type of organization is also referred to as bottom-up or top-down.

16
FIG.1 FEED-FORWARD NETWORKS

17
2. FEEDBACK NETWORKS
 2. Feedback Networks

Figure 2: An example of a simple feed forward network

18
Figure 3: An example of a complicated
network

19
 Feedback networks (figure 1) can have signals travelling in both directions by

introducing loops in the network.

 Feedback networks are very powerful and can get extremely complicated.

 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.

 Feedback architectures are also referred to as interactive or recurrent, although the

latter term is often used to denote feedback connections in single-layer organizations.

20
 SOME DIFFERENT APPLICATIONS


Character Recognition - The idea of character recognition has become very

important as handheld devices like the Palm Pilot are becoming increasingly

popular. Neural networks can be used to recognize handwritten characters.

Image Compression - Neural networks can receive and process vast amounts

of information at once, making them useful in image compression. With the

Internet explosion and more sites using more images on their sites, using

neural networks for image compression is worth a look.

Stock Market Prediction - The day-to-day business of the stock market is
extremely complicated. Many factors weigh in whether a given stock will go
up or down on any given day. Since neural networks can examine a lot of
information quickly and sort it all out, they can be used to predict stock prices.

Traveling Salesman Problem- Interestingly enough, neural networks can

solve the traveling salesman problem, but only to a certain degree of
approximation.

Medicine, Electronic Nose, Security, and Loan Applications - These are

some applications that are in their proof-of-concept stage, with the acceptance
of a neural network that will decide whether or not to grant a loan, something
that has already been used more successfully than many humans.
DATA PROCESSING

 Data processing is the collection and manipulation of

items of data to produce meaningful information.
 In this sense it can be considered a subset of information
processing, the change (processing) of information in
any manner detectable by an observer.

23
 DATA PROCESSING FUNCTIONS
  Validation – Ensuring that supplied data is "clean, correct and useful."
  Sorting – "arranging items in some sequence and/or in different sets."
  Summarization – reducing detail data to its main points.
  Aggregation – combining multiple pieces of data.
  Analysis – the collection, organization, analysis, interpretation and
presentation of data.
  Reporting – list detail or summary data or computed information.
  Classifying – separates data into various categories.

24
 DATA VISUALIZATION
 Data visualization refers to the techniques used to communicate data
or information by encoding it as visual objects contained in graphics.
 The goal is to communicate information clearly and efficiently to
users.
 A primary goal of data visualization is to communicate information
clearly and efficiently to users via the information graphics selected,
such as tables and charts.

25
DATA RELIABILITY

 Data reliability is the accuracy and completeness of computer-

processed data, given the uses, they are intended for.
 Data reliability is a state that exists when data is sufficiently
complete and error free to be convincing for its purpose and
context.
 In addition to being reliable, data must also meet other tests for

evidence.

26
ACCURATE:

  CONSISTENT - data was obtained and used in a manner that

is clear and well defined enough to yield similar results in similar
analysis.
  CORRECT - the data set reflects the data entered at the source
(or if available source documents) and/or properly represents the
intended (i.e. calculated) results.

27
28