PRESENTED BY- TAUSEEF AHAMDM.TECH (COMPUTER SC. & ENGINEERING)
COMPUTER ENGINEERING DEPARTMENTZAKIR HUSSAIN COLLEGE OF ENGG. & TECH.
A.M.U, ALIGARH
Genetic Algorithm
Outlines
A quick overview of GA Features of GA Various Methods of Population
Selection Anatomy Of GA An example of GA
References….
Adaptation in Neural and Artificial Systems, John Holland, 1975.
Genetic Algorithm in Search, Optimization and Machine Learning, David E. Goldberg, 1989.
C. Darwin. On the Origin of Species by Means of Natural Selection; or, the Preservation of flavored Races in the Struggle for Life. John Murray, London, 1859.
A quick overview of GA
Developed: USA in the 1970’s, by John Holland Holland’s original GA is now known as the
simple genetic algorithm (SGA) GA was inspired by process of biological
evolution It is based on the Darwin’s theory of “survival
of the fittest” : the better individuals have better chance of reproducing.
Features of GA
Used to solve Hard problems Maintains a POPULATION of solutions Solutions are encoded as
CHROMOSOMES REPRODUCTION creates a new
population members MUTATION and CROSSOVER occurs
during reproduction
Conceptual Algorithm
Population Selection
stochastically select from one generation to create the basis of the next generation
The requirement is that the fittest individuals have a greater chance of survival than weaker ones
fitter individuals will tend to have a better probability of survival and will go forward to form the mating pool for the next generation
Various Methods of population Selection
a) Roulette Wheel selection b) Rank Selection c) Tournament Selection d) Elitism There are many other methods,
but we will discuss briefly only these methods.
Roulette Wheel selection(Example)
Fitness f(x) of individual No. 3 is the fittest and No. 2 is the weakest
Strongest individual a value of 38% and the weakest 5%
These percentage fitness values can then be used to configure the roulette wheel
Number of times the roulette wheel is spun is equal to size of the population
Each time the wheel stops this gives the fitter individuals the greatest chance of being selected for the next generation and subsequent mating pool.
Individual No. 3: 01000001012 will become more prevalent in the general population because it is fitter
Tournament Selection Provides Selective pressure by holding
a tournament competition among n individuals
Best individual from tournament is one having highest fitness, which is the winner of tournament
Tournament competitions and winner is then inserted into mating pool
Tournament selection( Example)
Rank Selection previous selection will have problems
when the fatnesses differs very much For example, if the best chromosome
fitness is 90% of all the roulette wheel then the other chromosomes will have very few chances to be selected
first ranks the population and then every chromosome receives fitness from this ranking
The worst will have fitness 1, second worst 2 etc. and the best will have fitness N(number of chromosomes in population).
Elitism Copies the best chromosome to new
offspring before the mutation and crossover
When creating a new population by crossover or mutation the best chromosome might be lost
Forces GA to retain some numbers of best individuals at each generation
Has been found that Elitism improves the performance significantly
An Example
Simple problem: max x2 over {0,1,…,31}
GA approach: Representation: binary code, e.g. 01101
13 Population size: 4 1-point xover, bitwise mutation Roulette wheel selection Random initialisation
We show one generational cycle done by hand
x2 example: selection
X2 example: crossover
Thank you……