TensorGP - Genetic Programming Engine in TensorFlow

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Baeta:2021:evoapplications,

• author = "Francisco Baeta and Joao Correia and Tiago Martins and Penousal Machado",
• title = "{TensorGP} - Genetic Programming Engine in {TensorFlow}",
• booktitle = "24th International Conference, EvoApplications 2021",
• year = "2021",
• month = "7-9 " # apr,
• editor = "Pedro Castillo and Juanlu Jimenez-Laredo",
• series = "LNCS",
• volume = "12694",
• publisher = "Springer Verlag",
• address = "virtual event",
• pages = "763--778",
• organisation = "EvoStar, Species",
• keywords = "genetic algorithms, genetic programming, Parallelisation, Vectorisation, TensorFlow, GPU computing",
• isbn13 = "978-3-030-72698-0",
• DOI = "doi:10.1007/978-3-030-72699-7_48",
• abstract = "we resort to the TensorFlow framework to investigate the benefits of applying data vectorisation and fitness caching methods to domain evaluation in Genetic Programming. For this purpose, an independent engine was developed, TensorGP, along with a testing suite to extract comparative timing results across different architectures and amongst both iterative and vectorized approaches. Our performance benchmarks demonstrate that by exploiting the TensorFlow eager execution model, performance gains of up to two orders of magnitude can be achieved on a parallel approach running on dedicated hardware when compared to a standard iterative approach.",
• notes = "http://www.evostar.org/2021/ EvoApplications2021 held in conjunction with EuroGP'2021, EvoCOP2021 and EvoMusArt2021",

}

Genetic Programming entries for Francisco Baeta Joao Nuno Goncalves Costa Cavaleiro Correia Tiago Martins Penousal Machado

Citations