Skip to main content

Revisiting the Sequential Symbolic Regression Genetic Programming

Oliveira, Luiz Otavio V.B., Otero, Fernando E.B., Miranda, Luis F., Pappa, Gisele L. (2016) Revisiting the Sequential Symbolic Regression Genetic Programming. In: 2016 5th Brazilian Conference on Intelligent Systems (BRACIS). . pp. 163-168. IEEE ISBN 978-1-5090-3567-0. E-ISBN 978-1-5090-3566-3. (doi:10.1109/BRACIS.2016.039)

Abstract

Sequential Symbolic Regression (SSR) is a technique that recursively induces functions over the error of the current solution, concatenating them in an attempt to reduce the error of the resulting model. As proof of concept, the method was previously evaluated in one-dimensional problems and compared with canonical Genetic Programming (GP) and Geometric Semantic Genetic Programming (GSGP). In this paper we revisit SSR exploring the method behaviour in higher dimensional, larger and more heterogeneous datasets. We discuss the difficulties arising from the application of the method to more complex problems, e.g., overfitting, along with suggestions to overcome them. An experimental analysis was conducted comparing SSR to GP and GSGP, showing SSR solutions are smaller than those generated by the GSGP with similar performance and more accurate than those generated by the canonical GP.

Item Type: Conference or workshop item (Paper)
DOI/Identification number: 10.1109/BRACIS.2016.039
Uncontrolled keywords: semantics; training; genetic programming; time series analysis; measurement; boosting; machine learning algorithm
Subjects: Q Science > Q Science (General) > Q335 Artificial intelligence
Divisions: Faculties > Sciences > School of Computing > Computational Intelligence Group
Faculties > Sciences > School of Computing > Data Science
Depositing User: Fernando Otero
Date Deposited: 30 Nov 2016 13:36 UTC
Last Modified: 14 Oct 2019 20:26 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/59290 (The current URI for this page, for reference purposes)
Otero, Fernando E.B.: https://orcid.org/0000-0003-2172-297X
  • Depositors only (login required):

Downloads

Downloads per month over past year