Local evolutionary search enhancement by random memorizing
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1141, 547-552
- https://doi.org/10.1109/icec.1998.700087
Abstract
For the calibration of laser induced plasma spectrometers robust and efficient local search methods are required. Therefore, several local optimizers from nonlinear optimization, random search and evolutionary computation are compared. It is shown that evolutionary algorithms are superior with respect to reliability and efficiency. To enhance the local search of an evolutionary algorithm a new method of random memorizing is introduced. This method is applied to one of the most simple evolutionary algorithm, the (1+1)-Evolution Strategy. It leads to a substantial gain in efficiency for a reliable local search. Finally, laser induced plasma spectroscopy and the calibration of a real example are sketched.Keywords
This publication has 7 references indexed in Scilit:
- Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A preliminary investigation into directed mutations in evolutionary algorithmsLecture Notes in Computer Science, 1996
- Gene pool recombination and utilization of covariances for the Breeder Genetic AlgorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Toward a Theory of Evolution Strategies: Some Asymptotical Results from the (1,+ λ)-TheoryEvolutionary Computation, 1993
- A Modification of Davidon's Minimization Method to Accept Difference Approximations of DerivativesJournal of the ACM, 1967
- A Simplex Method for Function MinimizationThe Computer Journal, 1965
- An efficient method for finding the minimum of a function of several variables without calculating derivativesThe Computer Journal, 1964