# NAME

Algorithm::Evolutionary::Op::Canonical_GA_NN - Canonical Genetic Algorithm that does not rank population

# SYNOPSIS

```
# Straightforward instance, with all defaults (except for fitness function)
my $algo = new Algorithm::Evolutionary::Op::Canonical_GA_NN;
#Define an easy single-generation algorithm with predefined mutation and crossover
my $m = new Algorithm::Evolutionary::Op::Bitflip; #Changes a single bit
my $c = new Algorithm::Evolutionary::Op::QuadXOver; #Classical 2-point crossover
my $generation = new Algorithm::Evolutionary::Op::Canonical_GA_NN( 0.2, [$m, $c] );
my $generation = new Algorithm::Evolutionary::Op::Canonical_GA_NN( undef , [$m, $c] ); # Defaults to 0.4
```

# Base Class

Algorithm::Evolutionary::Op::Base

# DESCRIPTION

The canonical classical genetic algorithm evolves a population of bitstrings until they reach the optimum fitness. It performs mutation on the bitstrings by flipping a single bit, crossover interchanges a part of the two parents.

The first operator should be unary (a la mutation) and the second binary (a la crossover) they will be applied in turn to couples of the population.

This is a fast version of the canonical GA, useful for large populations, since it avoids the expensive rank operation. Roulette wheel selection, still, is kind of slow.

# METHODS

## new( [ $selection_rate][,$operators_ref_to_array] )

Creates an algorithm, with the usual operators. Includes a default mutation and crossover, in case they are not passed as parameters. The first element in the array ref should be an unary, and the second a binary operator. This binary operator must accept parameters by reference, not value; it will modify them. For the time being, just Algorithm::Evolutionary::Op::QuadXOver works that way.

## apply( $population)

Applies a single generation of the algorithm to the population; checks that it receives a ref-to-array as input, croaks if it does not. This population should be already evaluated. Returns a new population for next generation, unsorted.

# SEE ALSO

- Algorithm::Evolutionary::Op::Easy
- Algorithm::Evolutionary::Wheel
- Algorithm::Evolutionary::Fitness::Base
- Of course, Algorithm::Evolutionary::Fitness::CanonicalGA

You will also find a canonical-genetic-algorithm.pl example within this bundle. Check it out for usage examples

# Copyright

```
This file is released under the GPL. See the LICENSE file included in this distribution,
or go to http://www.fsf.org/licenses/gpl.txt
```