Neural Networks. R & G Chapter 8 8.1 Feed-Forward Neural Networks otherwise known as The...

Neural Networks. R & G Chapter 8

•8.1 Feed-Forward Neural Networks

otherwise known as

•The Multi-layer Perceptron

or

•The Back-Propagation Neural Network

Figure 8.1 A fully connected feed-forward neural network

Node 1

Node 2

Node i

Node j

Node k

Node 3

Input Layer Output LayerHidden Layer

1.0

0.7

0.4

Wjk

Wik

W3i

W3j

W2i

W2j

W1i

W1j

A diagramatic representation of a Feed-Forward NN

x1=

x2=

x3=

y

Inputs and outputs are numeric.

Inputs and outputs

• Must be numeric, but can have any range in general.

• However, R &G prefer to consider constraining to (0-1) range inputs and outputs.

Equation 8.1

Neural Network Input Format

Real input data values are standardized (scaled) so that they all have ranges from 0 – 1.

valueattribute possiblelargest theis uemaximumVal

attribute for the valuepossiblesmallest theis ueminimumVal

converted be to value theis lueoriginalVa

range interval [0,1] thein falling valuecomputed theis newValue

where

ueminimumValuemaximumVal

ueminimumVallueoriginalVanewValue

Categorical input format• We need a way to convert categores to numberical values.

• For “hair-colour” we might have values: red, blond, brown, black, grey.

3 APPROACHES:

• 1. Use of (5) Dummy variables (BEST):

Let XR=1 if hair-colour = red, 0 otherwise, etc…

• 2. Use a binary array: 3 binary inputs can represent 8 numbers. Hence let red = (0,0,0), blond, (0,0,1), etc…

However, this sets up a false associations.

• 3. VERY BAD: red = 0.0, blond = 0.25, … , grey = 1.0

Converts nominal scale into false interval scale.

Equation 8.2

Calculating Neuron Output:The neuron threshhold function. The following sigmoid function, called the standard logistic function, is often used to model the effect of a neuron.

3

1,,0,3,2,1,0

321in

iiniiiiixinwwxwxwxwwx

...718.2;1

1)(

e

exf

x

Consider node i, in the hidden layer. It has inputs x1, x2, and x3, each with a weight-parameter.

Then calculate the output from the following function:

Figure 8.2 The sigmoid function

0.000

0.200

0.400

0.600

0.800

1.000

1.200

-6 -5 -4 -3 -2 -1 0 1 2 3 4 5 6

f(x)

x

Note: the output values are in the range (0,1).

This is fine if we want to use our output to predict a probability of an event happening.

.

Other output types• If we have a categorical output with several values, then

we can use dummy output notes for each value of the attribute.

E.g. if we were predicting one of 5 hair-colour classes, we would have 5 output nodes, with 1 being certain yes, and 0 being certain no..

• If we have a real output variable, with values outside the range (0-1), then another transformation would be needed to get realistic real outputs. Usually the inverse of the scaling transformation. i.e.

rangeoutputvalueoutput *))10((min

Table 8.1 • Initial Weight Values for the Neural Network Shown in Figure 8.1

Wlj

Wli

W2j

W2i

W3j

W3i

Wjk

Wik

0.20 0.10 0.30 –0.10 –0.10 0.20 0.10 0.50

•The performance parameters of the feed-forward neural network are the weights.

•The weights have to be varied so that the predicted output is close to the true output value corresponding to the inpute values.

•Training of the ANN (Artificial Neural Net) is effected by:

• Starting with artibrary wieghts

• Presenting the data, instance by instance

• adapting the weights according the error for each instance.

•Repeating until convergence.

Training the Feed-forward net

8.2 Neural Network Training: A Conceptual View

Supervised Learning/Training with Feed-Forward Networks

• Backpropagation LearningCalculated error of each instance is used to ammend weights.

• Least squares fitting.All the errors for all instances are squared and summed

(=ESS). All weights are then changed to lower the ESS.

BOTH METHODS GIVE THE SAME RESULTS.

IGNOR THE R & G GENETIC ALGORITHM STUFF.

Unsupervised Clustering with Self-Organizing Maps

Figure 8.3 A 3x3 Kohonen network with two input layer nodes

Output Layer

Input Layer

Node 2Node 1

r

x

n

n

n’= n + r*(x-n)

Data Instance

8.3 Neural Network Explanation

• Sensitivity Analysis

• Average Member Technique

8.4 General Considerations

• What input attributes will be used to build the network? • How will the network output be represented?• How many hidden layers should the network contain?• How many nodes should there be in each hidden layer?• What condition will terminate network training?

Neural Network Strengths

• Work well with noisy data.• Can process numeric and categorical data.• Appropriate for applications requiring a time element.• Have performed well in several domains.• Appropriate for supervised learning and unsupervised

clustering.

Weaknesses

• Lack explanation capabilities.• May not provide optimal solutions to problems.• Overtraining can be a problem.

Building Neural Networks with iDA

Chapter 9

9.1 A Four-Step Approach for Backpropagation Learning

1. Prepare the data to be mined.

2. Define the network architecture.

3. Watch the network train.

4. Read and interpret summary results.

Example 1: Modeling the Exclusive-OR Function

Table 9.1 • The Exclusive-OR Function

Input 1 Input 2 XOR

1 1 00 1 11 0 10 0 0

Figure 9.1A graph of the XOR function

0

0.2

0.4

0.6

0.8

1

1.2

0 0.2 0.4 0.6 0.8 1 1.2

Input 2

Input 1

A B

AB

Step 1: Prepare The Data To Be Mined

Figure 9.2 XOR training data

Step 2: Define The Network Architecture

Figure 9.3 Dialog box for supervised learning

Figure 9.4 Training options for backpropagation learning

Step 3: Watch The Network Train

Figure 9.5 Neural network execution window

Step 4: Read and Interpret Summary Results

Figure 9.6 XOR output file for Experiment 1

Figure 9.7 XOR output file for Experiment 2

Example 2: The Satellite Image Dataset

Step 1: Prepare The Data To Be Mined

Figure 9.8 Satellite image data

Step 2: Define The Network Architecture

Figure 9.9 Backpropagation learning parameters for the satellite image data

Step 3: Watch The Network Train

Step 4: Read And Interpret Summary Results

Figure 9.10 Statistics for the satellite image data

Figure 9.11 Satellite image data: Actual and computed output

9.2 A Four-Step Approach for Neural Network Clustering

Step 1: Prepare The Data To Be Mined

The Deer Hunter Dataset

Step 2: Define The Network Architecture

Figure 9.12 Learning parameters for unsupervised clustering

Step 3: Watch The Network Train

Figure 9.13 Network execution window

Step 4: Read And Interpret Summary Results

Figure 9.14 Deer hunter data: Unsupervised summary statistics

Figure 9.15 Output clusters for the deer hunter dataset

9.3 ESX for Neural Network Cluster Analysis