Improving the effectiveness of genetic programming using continuous self-adaptation

Thomas D. Griffiths*, Anikó Ekárt

*Corresponding author for this work

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

Abstract

Genetic Programming (GP) is a form of nature-inspired computing, introduced over 30 years ago, with notable success in problems such as symbolic regression. However, there remains a lot of relatively unexploited potential for solving hard, real-world problems. There is consensus in the GP community that the lack of effective real-world benchmark problems negatively impacts the quality of research [4]. When a GP system is initialised, a number of parameters must be provided. The optimal setup configuration is often not known, due to the fact that many of the values are problem and domain specific, meaning the GP system is unable to produce satisfactory results. We believe that the implementation of continuous self-adaptation, along with the introduction of tunable and suitably difficult benchmark problems, will allow for the creation of more robust GP systems that are resilient to failure.

Original languageEnglish
Title of host publicationArtificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers
PublisherSpringer
Pages97-102
Number of pages6
Volume732
ISBN (Print)9783319904177
DOIs
Publication statusE-pub ahead of print - 19 Apr 2018
Event2nd International Symposium on Artificial Life and Intelligent Agents, ALIA 2016 - Birmingham, United Kingdom
Duration: 14 Jun 201615 Jun 2016

Publication series

NameCommunications in Computer and Information Science
Volume732
ISSN (Print)1865-0929

Conference

Conference2nd International Symposium on Artificial Life and Intelligent Agents, ALIA 2016
CountryUnited Kingdom
CityBirmingham
Period14/06/1615/06/16

Fingerprint

Self-adaptation
Genetic programming
Genetic Programming
Benchmark
Symbolic Regression
Configuration
Computing

Keywords

  • Benchmarks
  • Genetic programming
  • Self-adaptation
  • Tartarus

Cite this

Griffiths, T. D., & Ekárt, A. (2018). Improving the effectiveness of genetic programming using continuous self-adaptation. In Artificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers (Vol. 732, pp. 97-102). (Communications in Computer and Information Science; Vol. 732). Springer. https://doi.org/10.1007/978-3-319-90418-4_8
Griffiths, Thomas D. ; Ekárt, Anikó. / Improving the effectiveness of genetic programming using continuous self-adaptation. Artificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers. Vol. 732 Springer, 2018. pp. 97-102 (Communications in Computer and Information Science).
@inproceedings{68e4f9f79b124ca4907e8302f50f2dbd,
title = "Improving the effectiveness of genetic programming using continuous self-adaptation",
abstract = "Genetic Programming (GP) is a form of nature-inspired computing, introduced over 30 years ago, with notable success in problems such as symbolic regression. However, there remains a lot of relatively unexploited potential for solving hard, real-world problems. There is consensus in the GP community that the lack of effective real-world benchmark problems negatively impacts the quality of research [4]. When a GP system is initialised, a number of parameters must be provided. The optimal setup configuration is often not known, due to the fact that many of the values are problem and domain specific, meaning the GP system is unable to produce satisfactory results. We believe that the implementation of continuous self-adaptation, along with the introduction of tunable and suitably difficult benchmark problems, will allow for the creation of more robust GP systems that are resilient to failure.",
keywords = "Benchmarks, Genetic programming, Self-adaptation, Tartarus",
author = "Griffiths, {Thomas D.} and Anik{\'o} Ek{\'a}rt",
year = "2018",
month = "4",
day = "19",
doi = "10.1007/978-3-319-90418-4_8",
language = "English",
isbn = "9783319904177",
volume = "732",
series = "Communications in Computer and Information Science",
publisher = "Springer",
pages = "97--102",
booktitle = "Artificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers",
address = "Germany",

}

Griffiths, TD & Ekárt, A 2018, Improving the effectiveness of genetic programming using continuous self-adaptation. in Artificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers. vol. 732, Communications in Computer and Information Science, vol. 732, Springer, pp. 97-102, 2nd International Symposium on Artificial Life and Intelligent Agents, ALIA 2016, Birmingham, United Kingdom, 14/06/16. https://doi.org/10.1007/978-3-319-90418-4_8

Improving the effectiveness of genetic programming using continuous self-adaptation. / Griffiths, Thomas D.; Ekárt, Anikó.

Artificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers. Vol. 732 Springer, 2018. p. 97-102 (Communications in Computer and Information Science; Vol. 732).

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

TY - GEN

T1 - Improving the effectiveness of genetic programming using continuous self-adaptation

AU - Griffiths, Thomas D.

AU - Ekárt, Anikó

PY - 2018/4/19

Y1 - 2018/4/19

N2 - Genetic Programming (GP) is a form of nature-inspired computing, introduced over 30 years ago, with notable success in problems such as symbolic regression. However, there remains a lot of relatively unexploited potential for solving hard, real-world problems. There is consensus in the GP community that the lack of effective real-world benchmark problems negatively impacts the quality of research [4]. When a GP system is initialised, a number of parameters must be provided. The optimal setup configuration is often not known, due to the fact that many of the values are problem and domain specific, meaning the GP system is unable to produce satisfactory results. We believe that the implementation of continuous self-adaptation, along with the introduction of tunable and suitably difficult benchmark problems, will allow for the creation of more robust GP systems that are resilient to failure.

AB - Genetic Programming (GP) is a form of nature-inspired computing, introduced over 30 years ago, with notable success in problems such as symbolic regression. However, there remains a lot of relatively unexploited potential for solving hard, real-world problems. There is consensus in the GP community that the lack of effective real-world benchmark problems negatively impacts the quality of research [4]. When a GP system is initialised, a number of parameters must be provided. The optimal setup configuration is often not known, due to the fact that many of the values are problem and domain specific, meaning the GP system is unable to produce satisfactory results. We believe that the implementation of continuous self-adaptation, along with the introduction of tunable and suitably difficult benchmark problems, will allow for the creation of more robust GP systems that are resilient to failure.

KW - Benchmarks

KW - Genetic programming

KW - Self-adaptation

KW - Tartarus

UR - http://www.scopus.com/inward/record.url?scp=85045978227&partnerID=8YFLogxK

UR - https://link.springer.com/chapter/10.1007%2F978-3-319-90418-4_8

U2 - 10.1007/978-3-319-90418-4_8

DO - 10.1007/978-3-319-90418-4_8

M3 - Conference contribution

AN - SCOPUS:85045978227

SN - 9783319904177

VL - 732

T3 - Communications in Computer and Information Science

SP - 97

EP - 102

BT - Artificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers

PB - Springer

ER -

Griffiths TD, Ekárt A. Improving the effectiveness of genetic programming using continuous self-adaptation. In Artificial Life and Intelligent Agents - Second International Symposium, ALIA 2016, Revised Selected Papers. Vol. 732. Springer. 2018. p. 97-102. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-319-90418-4_8