|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectec.BreedingSource
ec.SelectionMethod
ec.select.FitProportionateSelection
ec.select.SigmaScalingSelection
public class SigmaScalingSelection
Similar to FitProportionateSelection, but with adjustments to scale up/exaggerate differences in fitness for selection when true fitness values are very close to eachother across the population. This addreses a common problem with FitProportionateSelection wherein selection approaches random selection during late runs when fitness values do not differ by much.
Like FitProportionateSelection this is not appropriate for steady-state evolution. If you're not familiar with the relative advantages of selection methods and just want a good one, use TournamentSelection instead. Not appropriate for multiobjective fitnesses.
Note: Fitnesses must be non-negative. 0 is assumed to be the worst fitness.
Typical Number of Individuals Produced Per produce(...) call
Always 1.
Parameters
base.scaled-fitness-floor double = some small number (defaults to 0.1) |
(The sigma scaling formula sometimes returns negative values. This is unacceptable for fitness proportionate style selection so we must substitute the fitnessFloor (some value >= 0) for the sigma scaled fitness when that sigma scaled fitness <= fitnessFloor.) |
Default Base
select.sigma-scaling
Field Summary | |
---|---|
static java.lang.String |
P_SCALED_FITNESS_FLOOR
Scaled fitness floor |
static java.lang.String |
P_SIGMA_SCALING
Default base |
Fields inherited from class ec.select.FitProportionateSelection |
---|
fitnesses, P_FITNESSPROPORTIONATE |
Fields inherited from class ec.SelectionMethod |
---|
INDS_PRODUCED |
Fields inherited from class ec.BreedingSource |
---|
CHECKBOUNDARY, DEFAULT_PRODUCED, NO_PROBABILITY, P_PROB, probability, UNUSED |
Constructor Summary | |
---|---|
SigmaScalingSelection()
|
Method Summary | |
---|---|
Parameter |
defaultBase()
Returns the default base for this prototype. |
void |
prepareToProduce(EvolutionState s,
int subpopulation,
int thread)
A default version of prepareToProduce which does nothing. |
void |
setup(EvolutionState state,
Parameter base)
Sets up the BreedingPipeline. |
Methods inherited from class ec.select.FitProportionateSelection |
---|
finishProducing, produce |
Methods inherited from class ec.SelectionMethod |
---|
preparePipeline, produce, produces, typicalIndsProduced |
Methods inherited from class ec.BreedingSource |
---|
clone, getProbability, pickRandom, setProbability, setupProbabilities |
Methods inherited from class java.lang.Object |
---|
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
public static final java.lang.String P_SIGMA_SCALING
public static final java.lang.String P_SCALED_FITNESS_FLOOR
Constructor Detail |
---|
public SigmaScalingSelection()
Method Detail |
---|
public Parameter defaultBase()
Prototype
defaultBase
in interface Prototype
defaultBase
in class FitProportionateSelection
public void setup(EvolutionState state, Parameter base)
BreedingSource
The most common modification is to normalize it with some other set of probabilities, then set all of them up in increasing summation; this allows the use of the fast static BreedingSource-picking utility method, BreedingSource.pickRandom(...). In order to use this method, for example, if four breeding source probabilities are {0.3, 0.2, 0.1, 0.4}, then they should get normalized and summed by the outside owners as: {0.3, 0.5, 0.6, 1.0}.
setup
in interface Prototype
setup
in interface Setup
setup
in class BreedingSource
Prototype.setup(EvolutionState,Parameter)
public void prepareToProduce(EvolutionState s, int subpopulation, int thread)
SelectionMethod
prepareToProduce
in class FitProportionateSelection
|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |