Self-Organized Subpopulation Based on Multiple Features in Genetic Programming on GPU

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@Article{DBLP:journals/jaciii/OnoH21,

• author = "Keiko Ono and Yoshiko Hanada",
• title = "Self-Organized Subpopulation Based on Multiple Features in Genetic Programming on {GPU}",
• journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
• year = "2021",
• volume = "25",
• number = "2",
• pages = "177--186",
• month = mar,
• keywords = "genetic algorithms, genetic programming, GPU, parallel computing, island model, SoS-GP, subpopulation model, genetic diversity, multiple features, Newman clustering, CUDA, cuBLAST, cublasGetMatrix, symbolic regression",
• ISSN = "1343-0130",
• timestamp = "Mon, 12 Apr 2021 17:25:01 +0200",
• biburl = "https://dblp.org/rec/journals/jaciii/OnoH21.bib",
• bibsource = "dblp computer science bibliography, https://dblp.org",
• URL = "https://www.fujipress.jp/jaciii/jc/jacii002500020177/",
• DOI = "doi:10.20965/jaciii.2021.p0177",
• size = "10 pages",
• abstract = "Genetic Programming (GP) is an Evolutionary Computation (EC) algorithm. Controlling genetic diversity in GP is a fundamental requirement to obtain various types of local minima effectively; however, this control is difficult compared to other EC algorithms because of difficulties in measuring the similarity between solutions. In general, common subtrees and the edit distance between solutions is used to evaluate the similarity between solutions. However, there are no clear guidelines regarding the best features to evaluate it. We hypothesized that the combination of multiple features helps to express the specific genetic similarity of each solution. In this study, we propose a self-organized subpopulation model based on similarity in terms of multiple features. To reconstruct subpopulations, we introduce a novel weighted network based on each normalized feature and use network clustering techniques. Although we can regard similarity as a correlation network between solutions, the use of multiple features incurs high computational costs, however, calculating the similarity is very suitable for parallelisation on GPUs. Therefore, in the proposed method, we use CUDA to reconstruct subpopulations. Using three benchmark problems widely adopted in studies in the literature, we demonstrate that performance improvement can be achieved by reconstructing subpopulations based on a correlation network of solutions, and that the proposed method significantly outperforms typical methods.",
• notes = "p180 'Newman clustering can be applied to detect subpopulations in which individuals have a similar characteristic easily'

  'All our experiments were conducted on a single PC with 6 Intel Xeon E5-1660 3.3 GHz processors, with 24 GB of memory and NVIDIA Quadro K6000 running on Linux. The NVIDIA Quadro K6000 is capable of approximately 5.2 TFlops and 2880 CUDA cores'

  jacii002500020177

  Doshisha University, 1-3 Tatara Miyakodani, Kyotanabe, Kyoto 610-0394, Japan",

}

Genetic Programming entries for Keiko Ono Yoshiko Hanada

Citations