Practical Neural Network Recipies in C++

138

Chapter 8

Initialization

-

Randomly generate a population.

Evaluation - Test each individual, using the objective function.

Compute a fitness value, which is a measure of how well the

individual optimizes the function.

Parent selection

-

Choose pairs of individuals from the population in

such a way that those with higher fitness will be chosen more

often.

Reproduction - Generate (usually two) children from each pair of

parents. Each parent contributes half of its genetic makeup to

each child.

Mutation

-

Randomly change a tiny amount of the genetic information

in each child.

A complete pass through the above steps is a generation. After