Enhanced symbolic regression through local variable transformations

Jiří Kubalík, Erik Derner, Robert Babuška

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

5 Citations (Scopus)

Abstract

Genetic programming (GP) is a technique widely used in a range of symbolic regression problems, in particular when there is no prior knowledge about the symbolic function sought. In this paper, we present a GP extension introducing a new concept of local transformed variables, based on a locally applied affine transformation of the original variables. This approach facilitates finding accurate parsimonious models. We have evaluated the proposed extension in the context of the Single Node Genetic Programming (SNGP) algorithm on synthetic as well as real-problem datasets. The results confirm our hypothesis that the transformed variables significantly improve the performance of the standard SNGP algorithm.

Original languageEnglish
Title of host publicationProceedings of the 9th International Joint Conference on Computational Intelligence (IJCCI 2017)
PublisherSciTePress
Pages91-100
Volume1
ISBN (Print)978-989-758-274-5
DOIs
Publication statusPublished - 2017
EventIJCCI 2017: 9th International Joint Conference on Computational Intelligence - Funchal, Madeira, Portugal
Duration: 1 Nov 20173 Nov 2017

Conference

ConferenceIJCCI 2017: 9th International Joint Conference on Computational Intelligence
CountryPortugal
CityFunchal, Madeira
Period1/11/173/11/17

Keywords

  • Data-driven Modeling
  • Nonlinear Regression
  • Single Node Genetic Programming
  • Symbolic Regression

Fingerprint Dive into the research topics of 'Enhanced symbolic regression through local variable transformations'. Together they form a unique fingerprint.

  • Cite this

    Kubalík, J., Derner, E., & Babuška, R. (2017). Enhanced symbolic regression through local variable transformations. In Proceedings of the 9th International Joint Conference on Computational Intelligence (IJCCI 2017) (Vol. 1, pp. 91-100). SciTePress. https://doi.org/10.5220/0006505200910100