Page 316 -

Appendix B. CD Tools 305

- Error goal;
- Maximum number of iterations;
- Number of iterations between chart updates.

When back-propagation training is chosen, the following values must be
indicated:

- Learning rate;
- Learning rate increase;
- Learning rate decrease;
- Momentum factor;
- Maximum error ratio.

When genetic algorithm training is chosen, the following values must be
indicated:

- Initial population;
- Mutation rate;
- Crossover rate;
- Crossover type.

The following crossover types can be specified:
- 1 point crossover: change 1 point value between 2 population elements, using
the crossover rate as probability.
- 2 points crossover: change 2 point values between 2 population elements, using
the crossover rate as probability.
- Uniform crossover: perform a uniform change of point values between 2
population elements, using the crossover rate as probability.
- NN 1 point crossover: change the values corresponding to the weights and bias
of 1 neuron between 2 population elements, using the crossover rate as
probability.
- NN 2 points crossover: change the values corresponding to the weights and bias
of 2 neurons between 2 population elements, using the crossover rate as
probability.
- NN uniform crossover: perform a uniform change of the values corresponding
to the neurons' weights and bias between 2 population elements, using the
crossover rate as probability.
- Elitism: the population element with lowest error will always be transferred
without any change to the next generation.

The following training results appear in the training results frame and are
continuously updated during the learning process:

- Training set error;