Neural networks are a type of data mining technique inspired by biological neural systems. They are composed of interconnected nodes similar to neurons in the brain. Neural networks can learn patterns from complex data through supervised or unsupervised learning methods. They are widely used for applications like fraud detection, risk assessment, image recognition, and stock market prediction due to their ability to learn from examples without being explicitly programmed.

1. Neural Networks
By:
RIZWAN M H
DATAMINING & WAREHOUSING

2.  There are many ways of classifying the techniques
 These techniques consist of the specific algorithms
that can be used for each function
 Application areas where these techniques used:
 Fraud Detection
 Risk Assessment
 Market Analysis
Data Mining Techniques

3.  Cluster Detection
 Decision Trees
 Memory based Reasoning
 Link Analysis
 Neural Networks
 Genetic Algorithms
 Data Visualization
Data Mining Techniques

4.  Neural Networks is one of the Data Mining techniques.
 A Neural Networks is an information processing
paradigm that is inspired by biological nervous systems.
 The basic unit of a neural network (NN) is modeled after
the neurons in the brain.
 It is composed of a large number of highly
interconnected processing elements called neurons.
 This unit is known as node.
Neural Networks

5.  Neural Networks are analytic technique modelled after
the learning process
 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
Why Neural Networks.??

6. Neural Network Model
VIDEO

7.  Conventional computers use an algorithmic
approach, but neural networks works similar to
human brain and learns by example.
Neural Networks v/s Conventional
Computers

8. A simple neuron
 Takes the Inputs .
 Calculate the summation
of the Inputs .
 Compare it with the
threshold being set
during the learning stage.

9.  A firing rule determines how one calculates whether a
neuron should fire for any input pattern.
 Some sets cause it to fire (the 1-taught set of
patterns) and others which prevent it from doing so
(the 0-taught set)
Firing Rules

10. Example…
 For example, a 3-input
neuron is taught to
output 1 when the input
(X1,X2 and X3) is 111 or 101
and to output 0 when the
input is 000 or 001.
X
1:
0 0 0 0 1 1 1 1
X
2:
0 0 1 1 0 0 1 1
X
3:
0 1 0 1 0 1 0 1
O
U
T:
0 0
0/
1
0/
1
0/
1
1
0/
1
1

11. Example…
 After applying firing rule,
the truth table becomes,
 The difference between
the two truth tables is
called the generalisation
of the neuron.
X
1:
0 0 0 0 1 1 1 1
X
2:
0 0 1 1 0 0 1 1
X
3:
0 1 0 1 0 1 0 1
O
U
T:
0 0 0
0/
1
0/
1
1 1 1

12.  Fixed networks in which the weights cannot be
changed, ie dW/dt=0.
 In such networks, the weights are fixed a priori
according to the problem to solve.
 Adaptive networks which are able to change their
weights, ie dW/dt != 0.
Types of neural network

13. Associative mapping:
 Network learns to produce a particular pattern on the set
of input units whenever another particular pattern is
applied on the set of input units.
 Auto - Association
 Hetero - Association
The Learning Process

14. Auto-association:
 An input pattern is associated with itself and the states of
input and output units coincide. This is used to provide
pattern completion,
Associative Mapping

15. Hetero-association:
 Nearest-neighbour recall : the output pattern produced
corresponds to the input pattern stored, which is closest
to the pattern presented.
 Interpolative recall : where the output pattern is a
similarity dependent interpolation of the patterns stored
corresponding to the pattern presented.
Associative Mapping

16. • Supervised learning which incorporates an external
teacher, so that each output unit is told what its
desired response to input signals ought to be.
Supervised Learning

17. • During the learning process global information may
be required.
• Paradigms of supervised learning include error-
correction learning, reinforcement learning and
stochastic learning.
• An important issue concerning supervised learning is
the problem of error convergence.
• The aim is to determine a set of weights which
minimises the error.
Supervised Learning

18.  Unsupervised learning uses no external teacher and
is based upon only local information. It is also referred
to as self-organisation.
Unsupervised Learning

19.  We say that a neural network learns off-line if the
learning phase and the operation phase are distinct.
 A neural network learns on-line if it learns and
operates at the same time.
 Usually, supervised learning is performed off-line,
whereas unsupervised learning is performed on-line.
Unsupervised Learning

20.  The behaviour of an ANN (Artificial Neural Network)
depends on both the weights and the input-output
function (transfer function) that is specified for the units.
This function typically falls into one of three categories:
 linear (or ramp)
 threshold
 sigmoid
Transfer Function

21.  It calculates how the error changes as each weight is
increased or decreased slightly.
 The algorithm computes each EW by first computing
the EA, the rate at which the error changes as the
activity level of a unit is changed.
 For output units, the EA is simply the difference
between the actual and the desired output.
Back-propagation Algorithm

22.  The first step is to design a specific network architecture .
 The size and structure of the network needs to match the nature.
 The new network is then subjected to the process of "training“.
 After learning phase, the new network is ready and can be used
to generate predictions.
 The resulting "network" developed in the process of "learning"
represents a pattern detected in the data.
 One of the major advantages of neural networks is that, they are
capable of approximating any continuous function.
 An important disadvantage is that the final solution depends on
the initial conditions of the network.
Neural Networks works
VIDEO

23. Important Applications
 Finger print recognition system
 Preprocessing system
 Feature extraction using neural networks
 Classification
 result

24. Advantages
 Neural networks enable us to find solution where
algorithmic methods are computationally intensive or
do not exist.
 There is no need to program neural networks they
learn with examples.
 Neural networks offer significant speed advantage
over conventional techniques.

25. 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.
Some different applications

26. 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.
Travelling Salesman Problem- Interestingly enough, neural
networks can solve the travelling 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.