 A genetic operator is operator used in
genetic algorithms to guide the algorithm
towards a solution to a given problem.
 There are three main types of operators:
 Selection,
 Crossover,
 Mutation.
 Genetic operator are used to create and
maintain genetic diversity *(Mutation)
 Combine existing solution also known as
chromosomes
 Into a new solution*(Crossover)
 And select between solution*(selection)
 Mutation(or mutation-like)operators are said
to be *unary operators
 They only operate on one chromosome at a
time
 In contrast crossover operator are said to be
*binary operators
 As they operate on two chromosome into
existing chromosomes into one new
chromosomes
 Genetic variation is a necessity foe the
process of *evolution.
 Genetic operators used in genetic algorithm
are analogous to those in the natural world
 Survival of the selection ;
 Reproduction crossover also called
recombination and mutation.
 Selection operators give preference to better
solution(chromosomes)allowing them to
pass their “genes” to the next generation of
the algorithm
 The selection operator may also simply pass
the best solution from the current generation
directly to the next generation without being
mutated
 This is known as elitist selection.
 Cross over is the process of taking more
than one parent solution and producing child
solution from them.
 By recombine portion of good solution the
genetic algorithm is more likely to create a
better solution
 There are a number of different methods for
combining the parent solution including the
edge recombination operator(ERO) and the
‘cut and splice and uniform crossover
method’.
 Types of crossover:
 Single point crossover,
 Two point crossover,
 Uniform crossover.
 The mutation operator encourages genetic
diversity among solution and attempts to
prevent the genetic algorithm .
 Converging to a local minimum by stopping
the solution becoming too close to one
another.
 There are different methods of mutation may be
used, these are range from,
 Bit mutation,
 Flip bit mutation,
 Boundary mutation,
 Non uniform mutation,
 Uniform mutation,
 Gaussian mutation,
 shrink mutation.
 The operators must work in conjunction with
each other for the algorithm to be successful
in finding a good solution.
 Selection operator on its own will tend to fill
the solution population with copies of the
best solution from population.
 If the selection and crossover operators are
used without the mutation operator the
algorithm will tends to converge to a local
minimum.
 Using mutation operator on its own leads to
a random walk through the search space.
 Only by using all the three operators
together can genetic algorithm become a
“noise-tolerant hill-climbing algorithm”
 Yielding good solution to the problem...
THANK YOU....

Soft computing

  • 2.
     A geneticoperator is operator used in genetic algorithms to guide the algorithm towards a solution to a given problem.  There are three main types of operators:  Selection,  Crossover,  Mutation.
  • 3.
     Genetic operatorare used to create and maintain genetic diversity *(Mutation)  Combine existing solution also known as chromosomes  Into a new solution*(Crossover)  And select between solution*(selection)
  • 4.
     Mutation(or mutation-like)operatorsare said to be *unary operators  They only operate on one chromosome at a time  In contrast crossover operator are said to be *binary operators  As they operate on two chromosome into existing chromosomes into one new chromosomes
  • 5.
     Genetic variationis a necessity foe the process of *evolution.  Genetic operators used in genetic algorithm are analogous to those in the natural world  Survival of the selection ;  Reproduction crossover also called recombination and mutation.
  • 6.
     Selection operatorsgive preference to better solution(chromosomes)allowing them to pass their “genes” to the next generation of the algorithm  The selection operator may also simply pass the best solution from the current generation directly to the next generation without being mutated  This is known as elitist selection.
  • 7.
     Cross overis the process of taking more than one parent solution and producing child solution from them.  By recombine portion of good solution the genetic algorithm is more likely to create a better solution
  • 8.
     There area number of different methods for combining the parent solution including the edge recombination operator(ERO) and the ‘cut and splice and uniform crossover method’.  Types of crossover:  Single point crossover,  Two point crossover,  Uniform crossover.
  • 9.
     The mutationoperator encourages genetic diversity among solution and attempts to prevent the genetic algorithm .  Converging to a local minimum by stopping the solution becoming too close to one another.
  • 10.
     There aredifferent methods of mutation may be used, these are range from,  Bit mutation,  Flip bit mutation,  Boundary mutation,  Non uniform mutation,  Uniform mutation,  Gaussian mutation,  shrink mutation.
  • 11.
     The operatorsmust work in conjunction with each other for the algorithm to be successful in finding a good solution.  Selection operator on its own will tend to fill the solution population with copies of the best solution from population.  If the selection and crossover operators are used without the mutation operator the algorithm will tends to converge to a local minimum.
  • 12.
     Using mutationoperator on its own leads to a random walk through the search space.  Only by using all the three operators together can genetic algorithm become a “noise-tolerant hill-climbing algorithm”  Yielding good solution to the problem...
  • 13.