mutation_wgi: /wgi mutation for DE

In fcampelo/ExpDE: Modular Differential Evolution for Experimenting with Operators

Description

Implements the "/wgi/nvecs" mutation (weighted global intermediate) for the ExpDE framework. This variant is based on a recombination strategy known as "weighted global intermediate recombination" (see the References section for details)

Usage

mutation_wgi(X, mutpars)

Arguments

X	population matrix
mutpars	mutation parameters (see Mutation parameters for details)

Value

Matrix M containing the mutated population

Mutation Parameters

The mutpars parameter contains all parameters required to define the mutation. mutation_wgi() understands the following fields in mutpars:

• f : scaling factor for difference vector(s).
  Accepts numeric vectors of size 1 or nvecs.

• nvecs : number of difference vectors to use.
  Accepts 1 <= nvecs <= (nrow(X)/2 - 2)
  Defaults to 1.

References

D. Arnold, "Weighted multirecombination evolution strategies". Theoretical Computer Science 361(1): 18-37, 2006.

T. Glasmachers, C. Igel, "Uncertainty handling in model selection for support vector machines". Proc. International Conference on Parallel Problem Solving from Nature (PPSN'08), 185-194, 2008.

Author(s)

Felipe Campelo ([e-mail])

fcampelo/ExpDE documentation built on May 16, 2019, 12:04 p.m.