Genetic Algorithms

1. Genetic Algorithms Niranjan Kumar Das Roll No : 182814 Nepal College Of information Technology 2019-Feb-21

2. what is a genetic algorithm? • Basic idea: Simulate natural selection, where the population is composed of candidate solutions. • Focus is on evolving a population from which strong and diverse candidates can emerge via mutation and crossover (mating). • A genetic algorithm is a randomized heuristic search method used in artificial intelligence and computing. • It is used for finding optimized solutions to search problems based on the theory of natural selection and evolutionary biology.  • Genetic algorithms are excellent for searching through large and complex data sets

3. Concepts of Genetic Algorithm Initial Population . Selection Fitness Function Pairing and Crossover Survivor Selection Mutation Terminate

4. Genetic Algorithm • Optimization Algorithm • Based on Neural phenomenon • Nature inspired approach based on Darwin's law of survival of the fittest and bio-inspired operator`s such as pairing Crossover and Mutation

5. Optimization • Optimization is the process of making something betterfinding the values of inputs in such a way that we get the “best” output values

6. Terminology • Population • Chromosomes • Gene Gene Chromosome • Operators • Selection • Crossover • Mutation Population

7. Fitness Function • The Fitness Function is the function you want to optimize. Function which takes the solution as input and produces the stability of the solution as the output. 24 31% 23 29% 20 26% 11 14% Initial Population Fitness Function

8. Fitness Function Contd.. • For the 8-queens problem we use the number of nonattacking pairs of queens, which has a value of 28 for the solution. • The values of the four states are 24,23,20, and 11 • Fitness function : number of non-attacking pairs of queens • (min = 0, max = 8*7/2 = 28) • 24/(24+23+20+11) = 31% • 23/(24+23+20+11) = 29% etc.

9. Parent Selection Roulette Wheel Selection Fixed Point Spin the Roulette wheel selection

10. Parent Selection • Rank Selection : Remove the concept of a fitness value while selecting a parent. Every individual in the population is ranked according to their fitness.

11. Parent Selection • Stochastic Universal Sampling (SUS) : Multiple fixed points , all the parents are chosen in just one spin of the wheel. • Tournament Selection : Select K individuals from the population at random and select the best out of these to become a parent, same process is repeated for selecting the next parent.

12. Pairing and crossover • One point Crossover : A Random crossover point is selected and the tails of its two parents are swapped to get new off-springs.

13. Mutation • Bit Flip Mutation : Select one or more random bits and flip them. • Swap Mutation :

14. Survivor Selection • Age based selection • Fitness Based selection Offspring`s Population Existing Population New Population

15. Advantages of Genetic Algorithm • Does not require any derivative information. • Faster and more efficient as compared to the traditional methods. • Optimize both continuous and discrete functions and also multi-objective Problems. • Provides a list of “good” solutions and not just a single solution. • Useful when the search space is very large and there are a large number of parameters involved.

16. Limitations of Genetic Algorithm • Computationally expensive as fitness value is calculated repeatedly. • Not suited for all problems, especially problems which are simple and for which derivative information is available. • GA may not converge to the optimal solution, if not implemented properly.

17. .