NAME Algorithm::Evolutionary::Op::Breeder_Diverser - Like Breeder, only it tries to cross only individuals that are different

SYNOPSIS

use Algorithm::Evolutionary qw( Individual::BitString 
  Op::Mutation Op::Crossover
  Op::RouletteWheel
  Op::Breeder_Diverser);

use Algorithm::Evolutionary::Utils qw(average);

my @pop;
my $number_of_bits = 20;
my $population_size = 20;
my $replacement_rate = 0.5;
for ( 1..$population_size ) {
  my $indi = new Algorithm::Evolutionary::Individual::BitString $number_of_bits ; #Creates random individual
  $indi->evaluate( $onemax );
  push( @pop, $indi );
}

my $m =  new Algorithm::Evolutionary::Op::Mutation 0.5;
my $c = new Algorithm::Evolutionary::Op::Crossover; #Classical 2-point crossover

my $selector = new Algorithm::Evolutionary::Op::RouletteWheel $population_size; #One of the possible selectors

my $generation = 
  new Algorithm::Evolutionary::Op::Breeder_Diverser( $selector, [$m, $c] );

my @sortPop = sort { $b->Fitness() <=> $a->Fitness() } @pop;
my $bestIndi = $sortPop[0];
my $previous_average = average( \@sortPop );
$generation->apply( \@sortPop );

Base Class

Algorithm::Evolutionary::Op::Base

DESCRIPTION

Breeder part of the evolutionary algorithm; takes a population and returns another created from the first. Different from Algorithm::Evolutionary::Op::Breeder: tries to avoid crossover among the same individuals and also re-creating an individual already in the pool. In that sense it "diverses", tries to diversify the population. In general, it works better in environments where high diversity is needed (like, for instance, in Algorithm::MasterMind.

METHODS

new( $ref_to_operator_array[, $selector = new Algorithm::Evolutionary::Op::Tournament_Selection 2 ] )

Creates a breeder, with a selector and array of operators

apply( $population[, $how_many || $population_size] )

Applies the algorithm to the population, which should have been evaluated first; checks that it receives a ref-to-array as input, croaks if it does not. Returns a sorted, culled, evaluated population for next generation.

It is valid only for string-denominated chromosomes.

SEE ALSO

More or less in the same ballpark, alternatives to this one

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

CVS Info: $Date: 2012/05/15 11:58:01 $ 
$Header: /cvsroot/opeal/Algorithm-Evolutionary/lib/Algorithm/Evolutionary/Op/Breeder_Diverser.pm,v 1.5 2012/05/15 11:58:01 jmerelo Exp $ 
$Author: jmerelo $ 
$Revision: 1.5 $