Genetic Algorithm
- 1. GENETIC ALGORITHMSRohith NandakumarS7 CS06348
- 2. INTRODUCTIONGenes are the basic “instructions” for building an organismGene represents a specific trait of the organism. Ex: Eye colorA gene may have different settingsA chromosome is a sequence of genes
- 3. EVOLUTIONOrganisms (animals or plants) produce a number of offspring which are almost, but not entirely, like themselvesVariation may be due to mutation (random changes)Variation may be due to combination of some characteristics from each parentSome of these offspring may survive to produce offspring of their own - some won’tThe “better adapted” offspring are more likely to surviveOver time, later generations become better and better adaptedGenetic algorithms use this same process to “evolve” better programs
- 4. GENETIC ALGORITHMSInspired by Darwin's theory about evolutionTheyare a part of evolutionary computing, which is a rapidly growing area of artificial intelligenceIdea of evolutionary computing was introduced in the 1960s by I.RechenbergGenetic Algorithms (GAs) were invented by John HollandIn 1992 John Kozahas used genetic algorithm to evolve programs to perform certain tasks. He called his method "genetic programming" (GP) LISP programs were used, because programs in this language can expressed in the form of a "parse tree", which is the object the GA works on
- 5. THE BASIC ALGORITHMSuppose your “organisms” are 32-bit computer wordsYou want a string in which all the bits are onesHere’s how you can do it:Create 100 randomly generated computer wordsRepeatedly do the following:Count the 1 bits in each wordExit if any of the words have all 32 bits set to 1Keep the ten words that have the most 1s (discard the rest)From each word, generate 9 new words as follows:Choose one of the other wordsTake the first half of this word and combine it with the second half of the other wordPick a random bit in the word and toggle (change) itNote that this procedure does not guarantee that the next “generation” will have more 1 bits, but it’s likely
- 6. ENCODINGThe chromosome should in some way contain information about solution which it representsThe most used way of encoding is a binary string. The chromosome then could look like this:Each chromosome has one binary stringEach bit in this string can represent some characteristic of the solution. Or the whole string can represent a number.
- 7. CROSSOVERCrossover selects genes from parent chromosomes and creates a new offspringA crossover point is chosen at randomEverything before this point, copy from a first parent and then everything after it copy from the second parent.There are other ways how to make crossoverSpecific crossover made for a specific problem can improve performance of the genetic algorithm
- 8. MUTATIONMutation prevents the algorithm to be trapped in a local minimaChanges are made in the offspring randomlyThe mutation depends on the encoding as well as the crossover.
- 9. SELECTIONChromosomes are selected from the population to be parents to crossoverMain idea: better individuals get higher chance to reproduceChances proportional to fitnessImplementation: Roulette Wheel techniqueAssign to each individual a part of the roulette wheel
- 10. Spin the wheel n times to select n individualsAN EXAMPLE:TRAVELLING SALESMAN PROBLEM
- 11. INITIAL POPULATION FOR TSP(5,3,4,6,2)(2,4,6,3,5)(4,3,6,5,2)(2,3,4,6,5)(4,3,6,2,5)(3,4,5,2,6)(3,5,4,6,2)(4,5,3,6,2)(5,4,2,3,6)(4,6,3,2,5)(3,4,2,6,5)(3,6,5,1,4)
- 12. SELECT PARENTS(5,3,4,6,2)(2,4,6,3,5)(4,3,6,5,2)(2,3,4,6,5)(4,3,6,2,5)(3,4,5,2,6)(3,5,4,6,2)(4,5,3,6,2)(5,4,2,3,6)(4,6,3,2,5)(3,4,2,6,5)(3,6,5,1,4)Try to pick the better ones.
- 17. ELIMINATE(5,3,4,6,2)(2,4,6,3,5)(4,3,6,5,2)(2,3,4,6,5)(2,3,6,4,5)(3,4,5,2,6)(3,5,4,6,2)(4,5,3,6,2)(5,4,2,3,6)(4,6,3,2,5)(3,4,2,6,5)(3,6,5,1,4)(3,4,5,6,2)(5,4,2,6,3)Tend to kill off the worst ones.
- 20. GENETIC PROGRAMMINGA string of bits could represent a programIf you want a program to do something, you might try to evolve oneAs a concrete example, suppose you want a program to help you choose stocks in the stock marketThere is a huge amount of data, going back many yearsWhat data has the most predictive value?What’s the best way to combine this data?A genetic program is possible in theory, but it might take years to evolve into something useful
- 21. APPLICATIONS OF GATravelling Salesman ProblemArtificial Life (A-Life)RoboticsAutomotive DesignEvolvable HardwareComputer GamingOptimizing Chemical Kinetic AnalysisEncryption and Code Breaking
- 22. CONCLUSIONGenetic algorithms are -Fun! They are enjoyable to program and to work withMind-bogglingly slow - you don’t want to use them if you have any alternativesGood for a very few types of problemsGenetic algorithms can sometimes come up with a solution when you can see no other way of tackling the problem
- 23. Q & A?
- 24. THANKYOU…