Towards identifying salient patterns in genetic programming individuals

András Joó*, Juan Pablo Neirotti

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A practical method for the offline extraction and analysis of salient patterns from tree-based genetic programming (GP) individuals is proposed. The method is contrasted with Tackett's algorithm [7] and it is shown that relying solely on frequency and fitness profiles for the salient pattern identification can be misleading. To amend Tackett's work a formula for measuring saliency is proposed. A method for separating inert and salient patterns is also discussed.

Original languageEnglish
Title of host publicationProceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09
Place of PublicationNew York, NY (US)
PublisherACM
Pages1885-1886
Number of pages2
ISBN (Print)978-1-60558-325-9
DOIs
Publication statusPublished - 8 Jul 2009
Event11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009 - Montreal, QC, Canada
Duration: 8 Jul 200912 Jul 2009

Conference

Conference11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
CountryCanada
CityMontreal, QC
Period8/07/0912/07/09

Fingerprint

Genetic programming
Genetic Programming
Saliency
Fitness

Keywords

  • genetic programming
  • patterns
  • tree-mining

Cite this

Joó, A., & Neirotti, J. P. (2009). Towards identifying salient patterns in genetic programming individuals. In Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09 (pp. 1885-1886). New York, NY (US): ACM. https://doi.org/10.1145/1569901.1570217
Joó, András ; Neirotti, Juan Pablo. / Towards identifying salient patterns in genetic programming individuals. Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09. New York, NY (US) : ACM, 2009. pp. 1885-1886
@inproceedings{d1e8d6b08de642ecb86694716ab249ab,
title = "Towards identifying salient patterns in genetic programming individuals",
abstract = "A practical method for the offline extraction and analysis of salient patterns from tree-based genetic programming (GP) individuals is proposed. The method is contrasted with Tackett's algorithm [7] and it is shown that relying solely on frequency and fitness profiles for the salient pattern identification can be misleading. To amend Tackett's work a formula for measuring saliency is proposed. A method for separating inert and salient patterns is also discussed.",
keywords = "genetic programming, patterns, tree-mining",
author = "Andr{\'a}s Jo{\'o} and Neirotti, {Juan Pablo}",
year = "2009",
month = "7",
day = "8",
doi = "10.1145/1569901.1570217",
language = "English",
isbn = "978-1-60558-325-9",
pages = "1885--1886",
booktitle = "Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09",
publisher = "ACM",
address = "United States",

}

Joó, A & Neirotti, JP 2009, Towards identifying salient patterns in genetic programming individuals. in Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09. ACM, New York, NY (US), pp. 1885-1886, 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009, Montreal, QC, Canada, 8/07/09. https://doi.org/10.1145/1569901.1570217

Towards identifying salient patterns in genetic programming individuals. / Joó, András; Neirotti, Juan Pablo.

Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09. New York, NY (US) : ACM, 2009. p. 1885-1886.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Towards identifying salient patterns in genetic programming individuals

AU - Joó, András

AU - Neirotti, Juan Pablo

PY - 2009/7/8

Y1 - 2009/7/8

N2 - A practical method for the offline extraction and analysis of salient patterns from tree-based genetic programming (GP) individuals is proposed. The method is contrasted with Tackett's algorithm [7] and it is shown that relying solely on frequency and fitness profiles for the salient pattern identification can be misleading. To amend Tackett's work a formula for measuring saliency is proposed. A method for separating inert and salient patterns is also discussed.

AB - A practical method for the offline extraction and analysis of salient patterns from tree-based genetic programming (GP) individuals is proposed. The method is contrasted with Tackett's algorithm [7] and it is shown that relying solely on frequency and fitness profiles for the salient pattern identification can be misleading. To amend Tackett's work a formula for measuring saliency is proposed. A method for separating inert and salient patterns is also discussed.

KW - genetic programming

KW - patterns

KW - tree-mining

UR - http://dl.acm.org/citation.cfm?doid=1569901.1570217

UR - http://www.scopus.com/inward/record.url?scp=72749124955&partnerID=8YFLogxK

U2 - 10.1145/1569901.1570217

DO - 10.1145/1569901.1570217

M3 - Conference contribution

AN - SCOPUS:72749124955

SN - 978-1-60558-325-9

SP - 1885

EP - 1886

BT - Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09

PB - ACM

CY - New York, NY (US)

ER -

Joó A, Neirotti JP. Towards identifying salient patterns in genetic programming individuals. In Proceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO '09. New York, NY (US): ACM. 2009. p. 1885-1886 https://doi.org/10.1145/1569901.1570217