On Switching Selection Methods to Increase Parsimony Pressure

Allan de Lima, Samuel Carvalho, Douglas Mota Dias, Joseph P. Sullivan, Conor Ryan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We proposed a novel and simple selection system that alternates between tournament and Lexicase selection to tackle the bloat issue. In this way, we used Lexi2, an implementation of Lexicase with lexicographic parsimony pressure, adopting the number of nodes in our solutions as size measurement. In addition, we increased the parsimony pressure by adding a penalty, also based on the number of nodes, to the aggregated fitness score. We analysed different scenarios, including some without extra parameters, in five benchmark problems: 2-bit Multiplier, 5-bit Parity, Car Evaluation, LED and Heart Disease. We succeeded in all of them in at least one scenario, reducing the size significantly while maintaining fitness. Beyond error and size, we also included results for the average number of fitness cases used in each generation.

Original languageEnglish
Title of host publicationProceedings of the 15th International Joint Conference on Computational Intelligence, IJCCI 2023
EditorsNiki van Stein, Francesco Marcelloni, H. K. Lam, Marie Cottrell, Joaquim Filipe
PublisherScience and Technology Publications, Lda
Pages96-107
Number of pages12
ISBN (Electronic)9789897586743
DOIs
Publication statusPublished - 2023
Event15th International Joint Conference on Computational Intelligence, IJCCI 2023 - Hybrid, Rome, Italy
Duration: 13 Nov 202315 Nov 2023

Publication series

NameInternational Joint Conference on Computational Intelligence
ISSN (Electronic)2184-3236

Conference

Conference15th International Joint Conference on Computational Intelligence, IJCCI 2023
Country/TerritoryItaly
CityHybrid, Rome
Period13/11/2315/11/23

Keywords

  • Bloat
  • Lexicase
  • Tournament

Fingerprint

Dive into the research topics of 'On Switching Selection Methods to Increase Parsimony Pressure'. Together they form a unique fingerprint.

Cite this