Demonstrating constraints to diversity with a tunably difficult problem for genetic programming

Daida, Jason M.; Samples, Michael E.; Hart, Bradd; Halim, J.; Kumar, Ajay

doi:10.1109/cec.2004.1331036

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While this type of methodology is not new to science, it is rarely practiced in our field. Some notable exceptions to this trend are found in Daida et al [11], Daida, Samples et al [12], Luke & Panait [15], and Luke & Spector [16]. Why is the number of large multi-configuration studies relatively small?…”

Section: ( )mentioning

confidence: 83%

“…A number of authors [13,18,21] have studied selection and replacement methods from a mathematical perspective. Discussions of fitness distributions, loss of diversity, and ordinary differential approximations influence our understanding of these dynamics, but very few empirical studies have compared different strategies [11,12]. A number of authors have argued that maintaining genetic diversity is important to EC populations [e.g., 23], but the effects of correlating selection and replacement methods is not known.…”

Section: Parameter Sweep Examplesmentioning

confidence: 99%

See 1 more Smart Citation

Parameter sweeps for exploring GP parameters

Samples¹,

Daida²,

Byom³

et al. 2005

Proceedings of the 7th Annual Workshop on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

This paper describes our procedure and a software application for conducting large parameter sweep experiments in genetic and evolutionary computation research. Both procedure and software allows a researcher to examine multivariate nonlinearities that are common in genetic and evolutionary computation. Experiments of this nature are well suited to distributed computing environments (such as Grids and clusters) and we present an automated system for conducting parameter sweep experiments on heterogeneous networks. Emphasis is placed on experimental sampling, distributed robustness, and data analysis. The parameter sweep experimental procedure is easily applicable to any experiment involving computer simulations but is particularly well suited for evolutionary computation experiments.

show abstract

Section: ( )mentioning

confidence: 83%

Section: Parameter Sweep Examplesmentioning

confidence: 99%

Parameter sweeps for exploring GP parameters

Samples¹,

Daida²,

Byom³

et al. 2005

Proceedings of the 7th Annual Workshop on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…The test problem that we have designed is called Highlander and was first described in (Daida, Samples et al, 2004). The premise behind this problem is simple and starts with a set of N uniquely labeled nodes, all of which are distributed among M individuals in an initial population.…”

Section: Theory Concerning Networkmentioning

confidence: 99%