Improving NeuroEvolution Efficiency by Surrogate Model-Based Optimization with Phenotypic Distance Kernels

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

@InProceedings{Stork:2019:evoapplications,

• author = "Joerg Stork and Martin Zaefferer and Thomas Bartz-Beielstein",
• title = "Improving NeuroEvolution Efficiency by Surrogate Model-Based Optimization with Phenotypic Distance Kernels",
• booktitle = "22nd International Conference, EvoApplications 2019",
• year = "2019",
• month = "24-26 " # apr,
• editor = "Paul Kaufmann and Pedro A. Castillo",
• series = "LNCS",
• volume = "11454",
• publisher = "Springer Verlag",
• address = "Leipzig, Germany",
• pages = "504--519",
• organisation = "EvoStar, Species",
• keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, Neuroevolution, Surrogate models, Kernel Distance Optimization",
• isbn13 = "978-3-030-16691-5",
• DOI = "doi:10.1007/978-3-030-16692-2_34",
• abstract = "In NeuroEvolution, the topologies of artificial neural networks are optimized with evolutionary algorithms to solve tasks in data regression, data classification, or reinforcement learning. One downside of NeuroEvolution is the large amount of necessary fitness evaluations, which might render it inefficient for tasks with expensive evaluations, such as real-time learning. For these expensive optimization tasks, surrogate model-based optimization is frequently applied as it features a good evaluation efficiency. While a combination of both procedures appears as a valuable solution, the definition of adequate distance measures for the surrogate modelling process is difficult. In this study, we will extend cartesian genetic programming of artificial neural networks by the use of surrogate model-based optimization. We propose different distance measures and test our algorithm on a replicable benchmark task. The results indicate that we can significantly increase the evaluation efficiency and that a phenotypic distance, which is based on the behaviour of the associated neural networks, is most promising.",
• notes = "http://www.evostar.org/2019/cfp_evoapps.php EuroGP'2019 held in conjunction with EvoCOP2019, EvoMusArt2019 and EvoApplications2019",

}

Genetic Programming entries for Joerg Stork Martin Zaefferer Thomas Bartz-Beielstein

Citations