Evolutionary computation

In computer science evolutionary computation denotes a subfield of artificial intelligence (more particular computational intelligence) involving combinatorial optimization problems. Whereas evolutionary algorithms generally only include methods such as natural reproduction, mutation, recombination and survival of the fittest, evolutionary computation is loosely recognised by the following criteria:

• iterative progress, growth or development (see evolution)
• population based
• guided random processes
• often biologically inspired

This mostly involves metaheuristic methods such as:

• evolutionary algorithms - e.g. genetic algorithm, genetic programming, evolutionary programming, evolution strategy
• swarm intelligence - e.g. ant colony optimization, particle swarm optimization

and in a lesser extent also:

• self organizing maps, systems & networks - e.g. growing neural gas, competitive learning [1]
• artificial life, cultural algorithms & swarms

References

• IEEE Transactions on Evolutionary Computing[2]
• Evolutionary Computation Repository[3]