Introduction to NeuNet Pro
Table Of Contents

Introduction

What is Neural Net?

Suggested Uses

SFAM Classification

Back Propagation

NeuNet Overview

What is a Neural Network?

A neural network is a software (or hardware) simulation of a biological brain (sometimes called Artificial Neural Network or "ANN"). The purpose of a neural network is to learn to recognize patterns in your data. Once the neural network has been trained on samples of your data, it can make predictions by detecting similar patterns in future data. Software that learns is truly "Artificial Intelligence".

Neural networks are a branch of the field known as "Artificial Intelligence". Other branches include Case Based Reasoning, Expert Systems, and Genetic Algorithms. Related fields include Classical Statistics, Fuzzy Logic and Chaos Theory. A Neural network can be considered as a black box that is able to predict an output pattern when it recognizes a given input pattern. The neural network must first be "trained" by having it process a large number of input patterns and showing it what output resulted from each input pattern. Once trained, the neural network is able to recognize similarities when presented with a new input pattern, resulting in a predicted output pattern.

Neural networks are able to detect similarities in inputs, even though a particular input may never have been seen previously. This property allows for excellent interpolation capabilities, especially when the input data is noisy (not exact). Neural networks may be used as a direct substitute for autocorrelation, multivariable regression, linear regression, trigonometric and other regression techniques.

When a data stream is analyzed using a neural network, it is possible to detect important predictive patterns that were not previously apparent to a non-expert. Thus the neural network can act as an expert.

An Example Neural Network: Bank Loans
Imagine a highly experienced bank manager who must decide which customers will qualify for a loan. His decision is based on a completed application form that contains ten questions. Each question is answered by a number from 1 to 5 (some responses may be subjective in nature).

Early attempts at "Artificial Intelligence" took a simplistic view of this problem. The Knowledge Engineer would interview the bank manager(s) and decide that question one is worth 30 points, question two is worth 10 points, question three is worth 15 points,...etc. Simple arithmetic was used to determine the applicant's total rating. A hurdle value was set for successful applicants. This approach helped to give artificial intelligence a bad name.

The problem is that most real-life problems are non-linear in nature. Response #2 may be meaningless if both response #8 and #9 are high. Response #5 should be the sole criterion if both #7 and #8 are low.

Our ten question application has almost 10 million possible responses. The bank manager's brain contains a Neural Network that allows him to use "Intuition". Intuition will allow the bank manager to recognize certain similarities and patterns that his brain has become attuned to. He may never have seen this exact pattern before, but his intuition can detect similarities, as well as dealing with the non-linearities. He is probably unable (and unwilling) to explain the very complex process of how his intuition works. A complicated list of rules (called "Expert System") could be drawn up but these rules may give only a rough approximation of his intuition.

If we had a large number of loan applications as input, along with the manager's decision as output, a neural network could be "trained" on these patterns. The inner workings of the neural network have enough mathematical sophistication to reasonably simulate the expert's intuition.

Another Example: Real-Estate Appraisal
Consider a real-estate appraiser whose job is to predict the sale price of residential houses. As with the Bank Loans example, the input pattern consists of a group of numbers. (For example: number of bedrooms, number of stories, floor area, age of construction, neighborhood prices, size of lot, distance to schools, etc.). This problem is similar to the Bank Loans example, because it has many non-linearities, and is subject to millions of possible inputs patterns. The difference here is that the output prediction will consist of a calculated value -- the selling price of the house.
It is possible to train the neural network to simulate the opinion of an expert appraiser, or to predict the actual selling price.

Note:
The above examples use a hypothetical bank manager and real-estate appraiser. Similar examples could use a doctor, judge, scientist, detective, IRS agent, social worker, machine operator or other expert. Even the behavior of some non-human physical process could be modeled. NeuNet Pro includes several sample projects.

SEVEN PART USENET FAQ (comp.ai.neural-nets)

  1. Introduction
  2. Learning
  3. Generalization
  4. Books, data, etc.
  5. Free software
  6. Commercial software
  7. Hardware





A Complete Neural Network Development System

CorMac Technologies Inc.
34 North Cumberland Street ~ Thunder Bay ON P7A 4L3 ~ Canada
E m a i l