BAS 250Lesson 6: Neural Networks

This Week’s Learning Objectives

• Explain what a neural network is, how it is used, and

the benefits of using it

• Recognize the necessary format for data in neural

network data mining

• Interpret a neural network’s outputs and understand

how to apply them to a scoring data set for deployment

Neural networks, as the name implies, try to

mimic interconnected neurons in the brain in

order to make the algorithm capable of

complex learning for extracting patterns and

detecting trends.

Introduction to Neural Networks

• Neural networks can predict categories or classifications similarly to decision trees; however, they are better at finding the strength of connections between attributes

• Neural networks are not as limited regarding value ranges as some other methodologies

Introduction to Neural Networks

It is built upon the premise that real world data structures are complex, and thus it necessitates complex learning systems.

Usually regression is “one-shot”; you cannot “train” a regression model. In other words, regression cannot “learn”.

Neural Networks

A trained neural network can be viewed as an “expert” in

the category of information it has been given to analyze.

This expert system can provide projections given new

solutions to a problem and answer "what if" questions.

Flexible models for regression and classification

Higher predictive power than regression and classification

trees

Benefits of Neural Networks

• Neural network algorithms often employ a concept

called fuzzy logic • Fuzzy logic is an inferential, probability-based approach to

data comparisons

• Using fuzzy logic, one can infer, based on probabilities, the

strength of the relationship between attributes in data sets

Fuzzy Logic of Neural Networks

• Neural networks use what is called a ‘hidden layer’ to

compare all attributes in a data set to all other attributes

• Circles in the neural network graph are nodes

• Lines between nodes are called neurons• The thicker and darker the neuron is between nodes, the

stronger the affinity between those nodes.

Structure of Neural Networks

A typical neural network is composed of three

types of layers

o input layer: data

o hidden layer: data transformation and manipulation

o output layer

Structure of Neural Networks

A graphical view

of a neural

network, in

RapidMiner,

showing different

strength neurons

Structure of Neural Networks

• The number of hidden layers can be adjusted in a neural network using

the size parameter

• There is no hard-and-fast rule about the size one should use, but a

generally accepted guideline is that it should be a number between

the total number of variables and the number of values in the

dependent variable

Neural Networks Rules of Thumb

• The number of maximum iterations can also be adjusted during model

development to identify the maximum number of times a neural network

will run through comparisons of attribute values against the target

attribute’s values

• If the independent variables are good predictors of the dependent

variable, most neural network models will achieve convergence

before reaching the maximum number of iterations

Neural Networks Rules of Thumb

Convergence is when the model has

successfully developed profiles based on the

training observations that can be used to make

predictions for scoring data

Convergence

There are three types of layers, not three layers, in the

network. There may be more than one hidden layer and it

depends on how complex the researcher wants the model to

be.

Because the input and the output are mediated by the hidden

layer, neural networks are commonly seen as a “black box.”

Harder to interpret and understand

Drawbacks

Use it when predictive accuracy is the most important

objective

When you need a non-linear fit but do not want over-fitting

and want to avoid the tedious work

When you have mixed data type, such as nominal, ordinal,

and continuous, but want to avoid the laborious data

transformation

Recommendations

Summary - Learning Objectives• Explain what a neural network is, how it is used, and

the benefits of using it

• Recognize the necessary format for data in neural

network data mining

• Interpret a neural network’s outputs and understand

how to apply them to a scoring data set for deployment

“This workforce solution was funded by a grant awarded by the U.S. Department of Labor’s

Employment and Training Administration. The solution was created by the grantee and does not

necessarily reflect the official position of the U.S. Department of Labor. The Department of Labor

makes no guarantees, warranties, or assurances of any kind, express or implied, with respect to such

information, including any information on linked sites and including, but not limited to, accuracy of the

information or its completeness, timeliness, usefulness, adequacy, continued availability, or

ownership.”

Except where otherwise stated, this work by Wake Technical Community College Building Capacity in

Business Analytics, a Department of Labor, TAACCCT funded project, is licensed under the Creative

Commons Attribution 4.0 International License. To view a copy of this license, visit

http://creativecommons.org/licenses/by/4.0/

Copyright Information