Estratégias evolutivas com mutações governadas por distribuições estáveis

AUTOR(ES)

Agostinho Benigno Monteiro Gutierrez

DATA DE PUBLICAÇÃO

2007

RESUMO

Evolutionary strategies normally use the Gaussian distributions in order to control the mutations over real values. Since there are other kinds of distributions in nature and in mathematics, such as those of Cauchy, Lévy and S-Lévy, in addition to several stable distributions, it seems a natural step to extend the standard approach, by using an algorithm that would be based upon other existing distributions, or that would even allow the choice of a stable distribution in a self-adaptive way. Such an idea is briefly sketched herein, in the context of populations of individuals that evolve towards the minimum of a test function (namely, the n-dimensional Rastrigin, Rosenberg, Griewangk and Schwefel functions) by means of evolutionary strategies, whose mutations are guided by eight types of specific types of distributions and by a self-adaptive scheme over a subset of the possible stable distributions. During the evolution of the experiment a remarkable influence on the right choice of the distribution family can be noted related to the search for the global minimum of a test function. This is due to the diversity used in the form of distribution: asymmetric and long tale (Lévy) and symmetric with various type of tale on the others. The choice of the type of distribution occurs determining four parameters properly: stability rate, asymmetric, scale and position. The choice of the type of distribution occurs determining if the four parameters above mentiones are part of the chromosome that also contains the possible coordinates of the global minimum that will be mutated according to the chosen distribution. Having applied this different mutation in the evolutionary process will lead to the global minimum of the chosen test function. The results indicate that the combined use of stable distribution controlling the mutations of the coordinates can result in a performance improvement regarding the convergence and consequent determination of the solution, when applied to spatially constrained benchmark functions.

ASSUNTO(S)

estratégias evolutivas stable distributions engenharia eletrica mutations distribuições estáveis evolutionary strategies mutações

Documentos Relacionados

• Convergência, na distância Mallows, de cadeias de Markov para distribuições estáveis
• Estimação de estados harmônicos usando estratégias evolutivas
• Estrategias evolutivas para a rede optica a partir de aneis WDM
• Otimização H2 com controladores estaveis : uma abordagem por programação geometrica
• Sistemas de inclusões diferenciais governadas pelo p-Laplaciano.