Evolution strategy
In computer science, Evolution strategy (ES, from German Evolutionstrategie) is an optimization technique based on ideas of adaptation and evolution. It belongs to a more general class of Evolutionary computation. Evolution strategy uses primarily real-vector coding, mutation, recombination, and selection as its primary operators. Mutation is performed by adding a gaussian distributed random value. The step size (ie. the variance of this distribution) is usually adapted during the optimization, which should keep the evolutionary process within the Evolution Window.
See also Bionics
References - H.-G. Beyer and H.-P. Schwefel. Evolution Strategies: A Comprehensive Introduction. Journal Natural Computing, 1(1):3-52, 2002.
- Ingo Rechenberg: Evolutionsstrategie '94. Stuttgart: Frommann-Holzboog 1994.
- Hans-Paul Schwefel: Evolution and Optimum Seeking: New York: Wiley & Sons 1995.
|
|
