C++ Neural Networks and Fuzzy Logic: Preface

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

Trying the Noise and Momentum Features

You can test out the version 2 simulator, which you just compiled with the example that you saw at the

beginning of the chapter. You will find that there is a lot of trial and error in finding optimum values for

alpha, the noise factor, and beta. This is true also for the middle layer size and the number of middle layers.

For some problems, the addition of momentum makes convergence much faster. For other problems, you may

not find any noticeable difference. An example run of the five−character recognition problem discussed at the

beginning of this chapter resulted in the following results with beta = 0.1, tolerance = 0.001, alpha = 0.25,

NF = 0.1, and the layer sizes kept at 35 5 3.

—————————————————————————−

        done:   results in file output.dat

                training: last vector only

                not training: full cycle

                weights saved in file weights.dat

——>average error per cycle = 0.02993<—−

——>error last cycle = 0.00498<—−

−>error last cycle per pattern= 0.000996 <—−

——————>total cycles = 242 <—−

——————>total patterns = 1210 <—−

—————————————————————————−

The network was able to converge on a better solution (in terms of error measurement) in

one−fourth the number of cycles. You can try varying alpha and NF to see the effect on

overall simulation time. You can now start from the same initial starting weights by

specifying a value of 1 for the starting weights question. For large values of alpha and beta,

the network usually will not converge, and the weights will get unacceptably large (you will

receive a message to that effect).