Genetic Algorithms (or GAs) are “heuristic” search algorithms based on the ideas of “natural selection and genetics”. The basis of GAs is build to simulate processes in which natural systems evolve, specifically those that adhere to the principles by Charles Darwin. Therefore, they are an intelligent representation of random searches within an existing search space for solving problems. These GAs constantly outperform traditional methods and therefore are ever more commonly used.
Common applications of GAs:
- GAs as problem solvers
- GAs solving technical puzzles
- GAs as basis for machine learning
- GAs as a computational model of innovation and creativity
- Generate random initial population M(0)
- Calculate and save the fitness u(m) for each person m in current population M(t)
- Define selection probabilities p(m) for each person m in M(t) so that p(m) is proportional to u(m)
- Generate M(t+1) by selecting persona from M(t) to create offspring with genetic operators
- Repeat step 2 until correct solution is obtained.
Get your grade
or your money back
using our Essay Writing Service!
GAs are applied in many scientific, engineering, business and entertainment fields, including:
- Automatic Programming: GAs have been constructed to create better computer programs for specific tasks and to create other computational simulations.
- Machine and robot learning: GAs have been constructed for many machine- learning processes. GAs are also been constructed to help with desigingn neural networks.
- Economic models: GAs have been constructed to simulate processes of innovation and the progression of bidding strategies.
- Immune system models: GAs have constructed used to simulate many viewpoints of the natural immune system.
- Parents: 100 010111 011
Offspring: 100 011111 010
- Parents: 111000 111000111 111
Offspring: 111000 111000111 111
The idea of computer algorithms being based on the evolution of organisms may sound futuristic, but it is astonishing how extensively these algorithms are applied in so many areas!
http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/tcw2/report.html visited on 15.7.2008
http://www-optima.amp.i.kyoto-u.ac.jp/member/student/hedar/Hedar_files/go_files/Page770.htm visited on 18.7.2008
http://www.learnartificialneuralnetworks.com/geneticalg.html visited on 18.7.2008