C++ Neural Networks and Fuzzy Logic: Preface

Figure 12.2

  Sample screen output of the letter A from the input and weight vectors.

Figure 12.3

  Sample screen output of the letter X from the input and weight vectors.

Previous Table of Contents Next

Copyright ©

 IDG Books Worldwide, Inc.

C++ Neural Networks and Fuzzy Logic:Preface

Testing the Program

254

---

C++ Neural Networks and Fuzzy Logic

by Valluru B. Rao

MTBooks, IDG Books Worldwide, Inc.

ISBN: 1558515526   Pub Date: 06/01/95

Previous Table of Contents Next

Generalization versus Memorization

As mentioned in Chapter 11, you actually don’t desire the exact replication of the input pattern for the weight

vector. This would amount to memorizing of the input patterns with no capacity for generalization.

For example, a typical use of this alphabet classifier system would be to use it to process noisy data, like

handwritten characters. In such a case, you would need a great deal of latitude in scoping a class for a letter A.