C++ Neural Networks and Fuzzy Logic: Preface

Reduce Dimensionality

You should try to eliminate inputs wherever possible. This will reduce the dimensionality of the problem and

make it easier for your neural network to generalize. Suppose that you have three inputs, x, y and z and one

output, o. Now suppose that you find that all of your inputs are restricted only to one plane. You could

redefine axes such that you have x’ and y’ for the new plane and map your inputs to the new coordinates. This

changes the number of inputs to your problem to 2 instead of 3, without any loss of information. This is

illustrated in Figure 14.1.

Figure 14.1

  Reducing dimensionality from three to two dimensions.

Previous Table of Contents Next

Copyright ©

 IDG Books Worldwide, Inc.

C++ Neural Networks and Fuzzy Logic:Preface

Reduce Dimensionality

300

---