Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
BY M.Janani IE336/11L07
GENETIC ALGORITHM-INTRODUCTION
Inspired by Darwin's theory about evolution. Population based search (parallel)
simultaneous search from multiple points in search space useful in complex, unstructured search spaces (less prone to local failures)
GENETIC ALGORITHM-INTRODUCTION
Search objective
Fitness score for population members (fitness function)
[Replace] Use new generated population for a further run of algorithm [Test] If the end condition is satisfied, stop, and return the best solution in current population [Loop] Go to step 2
Basic Operation
Selection Recombination
String1 (f1) String2 (f2) String3 (f3) String4 (f4) ... ... StringN (fN)
Basic parameters
Crossover probability-: no crossover- offspring is exact copy of parents. crossover- offspring is made from parts of parents chromosome. crossover probability is 100%- all offspring is made by crossover & vice versa.
Basic parameters[Continued]
Mutation probability : says how often will be parts of chromosome mutated. no mutation,-offspring is taken after crossover (or copy) without any change. mutation is performed-part of chromosome is changed.
Other parameters
Population size : -says how many chromosomes are in population -Too many chromosomes, GA slows down. -After some limit, not useful to increase population size , because it does not make solving the problem faster.
Typical GA Run
Fitness Best Average
Generations
Operators: Selection
Fitness proportionate selection (fi/f ) number of reproductive trials for individuals
Selection
Premature converge Fitness scaling f = f - (2*avg. - max.)
Ranked fitness Elitism Steady-state selection Demetic grouping
Selection-Types
Roulette-wheel selection
(stochastic sampling with replacement) wheel spaced in proportion to fitness values N (pop size) spins of the wheel
Using GAs
population size mutation, crossover rates how many generations multiple runs
GA Application Examples
Function optimizers
difficult, discontinuous, multi-modal, noisy functions
Combinatorial optimization
layout of VLSI circuits, factory scheduling, traveling salesman problem
THANK YOU