EUVIMEDEUVIMED entdecken
Systematische Übersicht

A Systematic Literature Review of the Successors of “NeuroEvolution of Augmenting Topologies”

Evgenia Papavasileiou, Jan Cornelis, Bart Jansen

Evolutionary Computation · 2021-03 · 29 (1) · 1-73

DOI: 10.1162/evco_a_00282 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Evolutionary Computation, 2021-03. Verfasst von Evgenia Papavasileiou und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Brussels, B-1050, Belgium imec, Leuven, B-3001, Belgium epapavas@etrovu…. Hauptthemen laut MEDLINE: Algorithms, Neural Networks, Computer. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 184 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

NeuroEvolution (NE) refers to a family of methods for optimizing Artificial Neural Networks (ANNs) using Evolutionary Computation (EC) algorithms. NeuroEvolution of Augmenting Topologies (NEAT) is considered one of the most influential algorithms in the field. Eighteen years after its invention, a plethora of methods have been proposed that extend NEAT in different aspects. In this article, we present a systematic literature review (SLR) to list and categorize the methods succeeding NEAT. Our review protocol identified 232 papers by merging the findings of two major electronic databases. Applying criteria that determine the paper's relevance and assess its quality, resulted in 61 methods that are presented in this article. Our review article proposes a new categorization scheme of NEAT's successors into three clusters. NEAT-based methods are categorized based on 1) whether they consider issues specific to the search space or the fitness landscape, 2) whether they combine principles from NE and another domain, or 3) the particular properties of the evolved ANNs. The clustering supports researchers 1) understanding the current state of the art that will enable them, 2) exploring new research directions or 3) benchmarking their proposed method to the state of the art, if they are interested in comparing, and 4) positioning themselves in the domain or 5) selecting a method that is most appropriate for their problem.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsNeural Networks, ComputerBiological Evolution

Stichwörter der Autor:innen

NeuroEvolutionartificial neural networksencodinggenetic algorithmssystematic literature review.topology evolution

Autor:innen und Institutionen

  • Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Brussels, B-1050, Belgium imec, Leuven, B-3001, Belgium epapavas@etrovub.be.
  • Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Brussels, B-1050, Belgium jpcornel@etrovub.be.
  • Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel, Brussels, B-1050, Belgium imec, Leuven, B-3001, Belgium bjansen@etrovub.be.

Zitieren

APA

Papavasileiou, E., Cornelis, J., & Jansen, B. (2021). A Systematic Literature Review of the Successors of “NeuroEvolution of Augmenting Topologies”. Evolutionary Computation, 29(1), 1-73. https://doi.org/10.1162/evco_a_00282

Vancouver

Papavasileiou E, Cornelis J, Jansen B. A Systematic Literature Review of the Successors of “NeuroEvolution of Augmenting Topologies”. Evolutionary Computation. 2021;29(1):1-73. doi:10.1162/evco_a_00282

BibTeX
@article{Papavasileiou2021,
  author = {Papavasileiou, Evgenia and Cornelis, Jan and Jansen, Bart},
  title = {A Systematic Literature Review of the Successors of “NeuroEvolution of Augmenting Topologies”},
  journal = {Evolutionary Computation},
  year = {2021},
  volume = {29},
  number = {1},
  pages = {1--73},
  doi = {10.1162/evco_a_00282}
}
Kostenlos starten →