Linear Combinations of Features As Leaf Nodes in Symbolic Regression

Created by W.Langdon from gp-bibliography.bib Revision:1.4020

  author =       "Jan Zegklitz and Petr Posik",
  title =        "Linear Combinations of Features As Leaf Nodes in
                 Symbolic Regression",
  booktitle =    "Proceedings of the Genetic and Evolutionary
                 Computation Conference Companion",
  series =       "GECCO '17",
  year =         "2017",
  isbn13 =       "978-1-4503-4939-0",
  address =      "Berlin, Germany",
  pages =        "145--146",
  size =         "2 pages",
  URL =          "",
  DOI =          "doi:10.1145/3067695.3076009",
  acmid =        "3076009",
  publisher =    "ACM",
  publisher_address = "New York, NY, USA",
  keywords =     "genetic algorithms, genetic programming, symbolic
  month =        "15-19 " # jul,
  abstract =     "We propose a new type of leaf node for use in Symbolic
                 Regression (SR) that performs linear combinations of
                 feature variables (LCF). LCF's weights are tuned using
                 a gradient method based on back-propagation algorithm
                 known from neural networks. Multi-Gene Genetic
                 Programming (MGGP) was chosen as a baseline model. As a
                 sanity check, we experimentally show that LCFs improve
                 the performance of the baseline on a rotated toy SR
                 problem. We then perform a thorough experimental study
                 on a number of artificial and real-world SR benchmarks.
                 The usage of LCFs in MGGP statically improved the
                 results in 5 cases out of 9, while it worsen them in
                 only a single case.",
  notes =        "Also known as \cite{Zegklitz:2017:LCF:3067695.3076009}
                 GECCO-2017 A Recombination of the 26th International
                 Conference on Genetic Algorithms (ICGA-2017) and the
                 22nd Annual Genetic Programming Conference (GP-2017)",

Genetic Programming entries for Jan Zegklitz Petr Posik