A Study on the use of ``self-generation'' in memetic algorithms

Krasnogor, Natalio; Gustafson, Steven

doi:10.1023/b:naco.0000023419.83147.67

Cited by 93 publications

(56 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These combined observations suggest that, as the problems become more difficult, a better ''signal-to-noise ratio'' could be obtained in what pertains to matching island topologies to problem structure. A similar effect was identified by Krasnogor and Gustafson (2004) and Krasnogor (2004) when evolving specific local searchers for NK-landscape in Memetic Algorithms (Krasnogor 2012). We thus performed an extended set of experiments with harder instances that are described next.…”

Section: Batchmentioning

confidence: 52%

“…On the other hand, if the neighbours are chosen at random the problem can be NP-Hard (Weinberger 1996). Furthermore, the landscapes can be tuned from smooth to rugged by increasing the value of the parameter K. Krasnogor and Gustafson (2004) and Krasnogor (2004) showed that it was possible to evolve local searchers for Memetic Algorithms that would match the structure of the problem being solved, in particular, NK-landscape instances. In this paper we would like to evaluate whether one could match different island topologies to different instances of the NK-landscape.…”

Section: Onemax Benchmarkmentioning

confidence: 99%

“…In this paper we would like to evaluate whether one could match different island topologies to different instances of the NK-landscape. Thus, we study four different scenarios: low epistasis and poly-time solvable, high epistasis and poly-time solvable, low epistasis and NP-hard and high epistasis and NP-hard instances of the NK-landscape problem as done by Krasnogor and Gustafson (2004).…”

Section: Onemax Benchmarkmentioning

confidence: 99%

See 2 more Smart Citations

Matching island topologies to problem structure in parallel evolutionary algorithms

et al. 2013

Self Cite

View full text Add to dashboard Cite

In the context of Parallel Evolutionary Algorithms, it has been shown that different population structures induce different search performances. Nevertheless, no work has shown a clear cut evidence that there is a correlation between the solver's population structure and the problem's network structure. In this work, we verify this correlation performing a clear and systematic analysis of a large set of population structures (based on the well known b-graphs and NK-landscape problems. Furthermore, we go beyond our findings in these idealised experiments by analysing the performance of variable-topology EAs on a dynamic real-world problem, the Multi-Skills Call Centre.

show abstract

Section: Batchmentioning

confidence: 52%

Section: Onemax Benchmarkmentioning

confidence: 99%

Section: Onemax Benchmarkmentioning

confidence: 99%

See 1 more Smart Citation

Matching island topologies to problem structure in parallel evolutionary algorithms

et al. 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, there are methodologies that can cut across categories. For example, we can see hybrid methodologies that combine constructive with perturbation heuristics [51], or heuristic selection with heuristic generation [42,60,66,71].…”

Section: Hyper-heuristicsmentioning

confidence: 99%

Contrasting meta-learning and hyper-heuristic research: the role of evolutionary algorithms

Pappa

Ochoa

Hyde

et al. 2013

Genet Program Evolvable Mach

View full text Add to dashboard Cite

The fields of machine meta-learning and hyper-heuristic optimisation have developed mostly independently of each other, although evolutionary algorithms (particularly genetic programming) have recently played an important role in the development of both fields. Recent work in both fields shares a common goal, that of automating as much of the algorithm design process as possible. In this paper we first provide a historical perspective on automated algorithm design, and then we discuss similarities and differences between meta-learning in the field of supervised machine learning (classification) and hyper-heuristics in the field of optimisation. This discussion focuses on the dimensions of the problem space, the algorithm space and the performance measure, as well as clarifying important issues related to different levels of automation and generality in both fields. We also discuss important research directions, challenges and foundational issues in meta-learning and hyper-heuristic research. It is important to emphasize that this paper is not a survey, as several surveys on the areas of meta-learning and hyper-heuristics (separately) have been previously published. The main contribution of the paper is to contrast meta-learning and hyper-heuristics methods and concepts, in order to 123Genet Program Evolvable Mach DOI 10.1007/s10710-013-9186-9 promote awareness and cross-fertilisation of ideas across the (by and large, nonoverlapping) different communities of meta-learning and hyper-heuristic researchers. We hope that this cross-fertilisation of ideas can inspire interesting new research in both fields and in the new emerging research area which consists of integrating those fields.

show abstract

“…En el control auto-adaptativo, los parámetros entran a formar parte de la propia solución del problema y evolucionan con el algoritmo como cualquiera de las variables de diseño del problema original. Esta técnica ha sido utilizada con Algoritmos Genéticos (AG) incorporando parámetros a los cromosomas (Angeline, 1996;Robert et al, 1996;Herrera y Lozano, 1998;Smith, 2003;Krasnogor y Gustafson, 2004). En (Wu y Simpson, 2002) se utiliza el control auto-adaptativo para estimar el factor de penalización; en su trabajo hacen referencia a los autores de (Bäck et al, 1991) como los que introdujeron el concepto de coevolucionar, que no es otra cosa que la forma auto-adaptativa de gestionar los parámetros.…”

Section: Consideraciones Sobre Los Parámetros a Utilizarunclassified

Diseño óptimo de sistemas de distribución de agua mediante Agent Swarm Optimization

Arango¹

View full text Add to dashboard Cite

A Study on the use of ``self-generation'' in memetic algorithms

Cited by 93 publications

References 18 publications

Matching island topologies to problem structure in parallel evolutionary algorithms

Matching island topologies to problem structure in parallel evolutionary algorithms

Contrasting meta-learning and hyper-heuristic research: the role of evolutionary algorithms

Diseño óptimo de sistemas de distribución de agua mediante Agent Swarm Optimization

Contact Info

Product

Resources

About