|
|
This is only a preview of the paper
Click here to register and get the full text.
Existing members click here to login
|
|
|
A genetic algorithm is a computer simulation in which a population of abstract representations of candidate solutions to an optimization problem are stochastically selected, recombined, mutated, and then either eliminated or retained, based on their relative fitnesses. ... In natural systems, both the probability and nature of change are random. ... The effect of crossover is to mix existing genetic material (which presumably has some survival value, since the parent genotypes contributing that material have survived long enough to breed). ... Crossover accounts for almost all observed variation in living organisms; almost all variation in a child can be accounted for as some combination of characteristics of its parents. Many people believe that assortment is the defining characteristic of genetic algorithms. ... In many natural organisms, a genes effect may not depend on its location in the genome. Thus, sections of natural chromosomes can be removed, flipped over, and re-inserted without ill effect. ... But, using an inversion operator in a genetic algorithm is costly and the programming involved is difficult. ... These are inspired directly by natural systems. ...
Selection in the simple GA is based directly on fitness: given a population of individuals, the probability of a particular individual passing its genes into the next generation is directly proportional to its fitness.
Approximate Word count = 938
Approximate Pages = 3.8
(250 words per page double spaced)
|
|
|
|
|
|