C++ Neural Networks and Fuzzy Logic: Preface

1.  Using the weight change for the previous pattern.

2.  Using the weight change accumulated over the previous cycle.

Previous Table of Contents Next

Copyright ©

 IDG Books Worldwide, Inc.

C++ Neural Networks and Fuzzy Logic:Preface

Adding the Momentum Term

263

---

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

Although both of these implementations are valid, the second is particularly useful, since it adds a term that is

significant for all patterns, and hence would contribute to global error reduction. We implement the second

choice by accumulating the value of the current cycle weight changes in a vector called cum_deltas. The past

cycle weight changes are stored in a vector called past_deltas. These are shown as follows in a portion of the

layer.h file.

class output_layer:   public layer

{

protected:

       float * weights;

       float * output_errors; // array of errors at output

       float * back_errors; // array of errors back−propagated

       float * expected_values;      // to inputs

       float * cum_deltas;   // for momentum

       float * past_deltas;  // for momentum

  friend network;

...