|
Name
|
Description
|
|
TExecutionLimit
|
Defines the execution limit for the virtual machine
|
|
TExecutionState
|
Defines the execution state for a virtual machine
|
|
TGACrossoverMethod
|
Defines the different crossover boundaries that can be used in recombination (combining parts of two parent's chromosome to create a new chromosome) for the TRSCustomGeneticAlgorithm component
Crossover is one of the evolutionary biology techniques used by the genetic algorithm component, along with inheritance, mutation, and selection. In crossover, the genetic algorithm component splices out the first random n-bits of one parent and concatenates it with the last chromosomesize-n bits of the other parent. The chromosome size of the child is the same as its parents. The Crossover Method property controls how the break is selected: on a gene boundary, bit boundary, or byte, word, or longword boundary. Note that crossover on a non-gene boundary could possibly cause invalid gene values because the newly combined gene at the crossover point is a random mixture of bits from the 2 parents.
|
|
TGAFitnessMethod
|
Defines the type of fitness methods. It controls how the genetic algorithm component evolves: should it seek to maximize fitness or minimize fitness?
|
|
TGAGeneticOperation
|
Defines the types of genetic Operations that the genetic component performs.
Genetic algorithms and programs are computer science techniques that seek to solve optimization or search problems. They are inspired by evolutionary biology and approach the search problem as a task of evolving a group or population of candidate individuals through successive generations, selecting fitter (or better) child individuals for each generation, until a solution is found. It uses evolutionary biology techniques such as inheritance, mutation, selection, and crossover (also called recombination).
|
|
TGASelectionMethod
|
Defines how the genetic component selects individuals from the current generation to be used as parents of the next generation
|
|
TGeneType
|
Defines the simple types that can be used for Genes in the genetic algorithm component.
|
|
TGPBloatStrategy
|
Defines the strategies for combatting bloat (program growth without (significant) return in terms of fitness.) in genetic programming
|
|
TGPCrossoverMethod
|
Defines the crossover method used in genetic programming
|
|
TGPGeneticInstruction
|
Defines the type of genetic instructions (and tree nodes) in a genetic program
|
|
TGPInitializationMethod
|
Defines the initialization methods for initializing a genetic program tree.
|
|
TGPMutationMethod
|
Defines the different mutation methods the genetic programming component can perform
 Note
|
Point mutation is listed for completeness. However, with our engine it can happen as inversion as well. If point mutation is done as Inversion, its probability is controlled by the InversionProbability property. If point mutation is done as a mutation method, its probability is controlled by the MutationProbability and the MutationMethodWeights.
|
|
|
TGPPointMutationMethod
|
Defines how often the genetic programming component attemps point mutation in a tree
|
