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
Summary
You explored further the backpropagation algorithm in this chapter, continuing the discussion in Chapter 7.
• A momentum term was added to the training law and was shown to result in much faster
convergence in some cases.
• A noise term was added to inputs to allow training to take place with random noise applied. This
noise was made to decrease with the number of cycles, so that final stage learning could be done in a
noise−free environment.
• The final version of the backpropagation simulator was constructed and used on the example from
Chapter 12. Further application of the simulator will be made in Chapter 14.
• Several applications with the backpropagation algorithm were outlined, showing the wide
applicability of this algorithm.
Previous Table of Contents Next
Copyright ©
IDG Books Worldwide, Inc.
C++ Neural Networks and Fuzzy Logic:Preface
Summary
296
Do'stlaringiz bilan baham: |