Neural network

NEURAL NETWORKS
M.H.Vinay Charan 08P71A12C0

What is a Neural Network?

An artificial neural network (ANN), often just
called a "neural network" (NN), is a mathematical
model or computational model based on biological
`

neural networks, in other words, is an emulation of
biological neural system.

Data Mining

Data mining is the term used to describe the
process of extracting value from a database.
Four things are required to data-mine effectively:
`
• High-quality data.
• “right” data.
• Adequate sample size.
• Right tool.

Why Neural Network?

• Neural networks are useful for data mining and decision-
support applications.

• People are good at generalizing from experience.
`
• Computers excel at following explicit instructions over and
over.

• Neural networks bridge this gap by modeling, on a
computer, the neural behavior of human brains.

ANN Characteristics

• Neural networks are useful for pattern recognition
or data classification, through a learning process.

• Neural networks simulate biological systems,
`

where learning involves adjustments to the
synaptic connections between neurons.

Anatomy of ANN

• Neural Networks map a set of Input 0 Input 1 ... Input n

input-nodes to a set of output-
nodes Neural Network
• Number of inputs/outputs is `

variable Output 0 Output 1 ... Output m

• The Network itself is composed of
an arbitrary number of nodes with
an arbitrary topology.
6

Biological Background

• A neuron: many-inputs / one-output unit

• Output can be excited or not excited

• Incoming signals from other neurons determine if the
`

neuron shall excite ("fire")

• Output subject to attenuation in the synapses, which are
junction parts of the neuron

Neural Network Topologies

This is of two types:

Feed Forward Neural Networks:

• Unidirectional, No feedback, No cycles.
`

Recurrent Network:

• Bi-directional, feedback.

Training Of ANN

A neural network has to be configured such that
the application of a set of inputs produces the
desired set of outputs. `

„Train‟ the neural network by feeding it teaching
patterns and letting it change its weights according
to some learning rule.

Neural Network in Data Mining

• Feed Forward Neural Network:

The simplified process for training a FFNN is as follows:

1. Input data is presented to the network and propagated
`

through the network until it reaches the output layer. This
forward process produces a predicted output.

2. The predicted output is subtracted from the actual output
and an error value for the networks is calculated.


3. The neural network then uses supervised learning, which in
most cases is back propagation, to train the network. Back
propagation is a learning algorithm for adjusting the
`
weights. It starts with the weights between the output layer
PE‟s and the last hidden layer PE‟s and works backwards
through the network.

4. Once back propagation has finished, the forward process

• Back Propagation:

Is a common method of teaching artificial neural
networks how to perform a given task. The back
`
propagation algorithm is used in layered feedforward
ANNs.

The back propagation algorithm uses supervised
learning, which means that we provide the algorithm

Technique used:

1. Present a training sample to the neural network.

2. Compare the network's output to the desired output from that
sample. Calculate the error in each output neuron.
`

3. For each neuron, calculate what the output should have been, and
a scaling factor, how much lower or higher the output must be
adjusted to match the desired output. This is the local error.


4. Adjust the weights of each neuron to lower the local

error.

5. Assign "blame" for the local error to neurons at the
`

previous level, giving greater responsibility to

neurons connected by stronger weights.

6. Repeat the steps above on the neurons at the

Basics of a Node
Input 0 Input 1 ... Input n

• A node is an
W0 W1 ... Wn

element which Wb + +

performs a function `
fH(x)

Connection

y = fH(∑(wixi) + Wb) Output
Node

15

Simple Perceptron

• Binary logic Input 0 Input 1

application W0 W1

• fH(x) [linear threshold] ` Wb +

• Wi = random(-1,1)
fH(x)

• Y = u(W0X0 + W1X1
Output

+ Wb) 16

Algorithm
1. Initialize the weights in the network (often randomly)
2. repeat
* for each example e in the training set do
1. O = neural-net-output(network, e) ;
forward pass
2. T = teacher output for e
3. Calculate error (T - O) at the output units
4. Compute ‘delta_wi’ for all weights `
from hidden layer to output layer ;
backward pass
5. Compute delta_wi for all weights from input layer to hidden layer ;
backward pass continued
6. Update the weights in the network
* end
3. until all examples classified correctly or
stopping criterion satisfied
4. return(network)

Advantages

• High Accuracy: Neural networks are able to approximate complex
non-linear mappings
• Noise Tolerance: Neural networks are very flexible with respect to
incomplete, missing and noisy data.
`

• Independence from prior assumptions: Neural networks do not
make a priori assumptions about the distribution of the data, or the
form of interactions between factors.
• Ease of maintenance: Neural networks can be updated with fresh
data, making them useful for dynamic environments.

Applications

• Finance.

• Marketing.

• Human Resource. `

• Accounting.

Design Problems

• There are no general methods to determine the
optimal number of neurons necessary for solving
any problem. `

• It is difficult to select a training data set which
fully describes the problem to be solved.

Improving ANN

• Designing Neural Networks using Genetic
Algorithms.

• Neuro-Fuzzy Systems. `

Conclusion

There is rarely one right tool to use in data
mining; it is a question as to what is available
and what gives the “best” results. Many
`

articles, in addition to those mentioned in this
paper, consider neural networks to be a
promising data mining tool

Neural network

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to Neural network (20)

Recently uploaded (20)

Neural network