Professional Documents
Culture Documents
INFORMATION PROCESSING
1
Unit-8 Information Processing
Neural Network,
Processing,
Data Visualization and Reliability
Principles and Application domains.
2
INTRODUCTION
3
WHAT IS NEURAL NETWORK
An Artificial Neural Network (ANN) is an information processing
paradigm that is inspired by biological nervous systems.
extract patterns and detect trends that are too complex to be noticed by
either humans or other computer techniques.
Adaptive learning
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.
9
ANNs have been applied to an increasing number of real-world
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
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
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
19
Feedback networks (figure 1) can have signals travelling in both directions by
Feedback networks are very powerful and can get extremely complicated.
Feedback networks are dynamic; their 'state' is changing continuously until they
They remain at the equilibrium point until the input changes and a new equilibrium
needs to be found.
20
SOME DIFFERENT APPLICATIONS
important as handheld devices like the Palm Pilot are becoming increasingly
Image Compression - Neural networks can receive and process vast amounts
Internet explosion and more sites using more images on their sites, using
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
evidence.
26
ACCURATE:
27
28