EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Self-replicating artificial neural networks give rise to universal evolutionary dynamics

Boaz Shvartzman, Yoav Ram iD

PLOS Computational Biology · 2024

DOI: 10.1371/journal.pcbi.1012004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2024. Verfasst von Boaz Shvartzman und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Zoology, Faculty of Life Sciences, Tel Aviv University; Tel Aviv, Israel. Hauptthemen laut MEDLINE: Biological Evolution, Neural Networks, Computer. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Israel science foundation, Minerva Foundation, Amazon Web Services.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In evolutionary models, mutations are exogenously introduced by the modeler, rather than endogenously introduced by the replicator itself. We present a new deep-learning based computational model, the self-replicating artificial neural network (SeRANN). We train it to (i) copy its own genotype, like a biological organism, which introduces endogenous spontaneous mutations; and (ii) simultaneously perform a classification task that determines its fertility. Evolving 1,000 SeRANNs for 6,000 generations, we observed various evolutionary phenomena such as adaptation, clonal interference, epistasis, and evolution of both the mutation rate and the distribution of fitness effects of new mutations. Our results demonstrate that universal evolutionary phenomena can naturally emerge in a self-replicator model when both selection and mutation are implicit and endogenous. We therefore suggest that SeRANN can be applied to explore and test various evolutionary dynamics and hypotheses.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biological EvolutionNeural Networks, ComputerMutation RateMutationGenotypeEvolution, Molecular

Autor:innen und Institutionen

  • School of Zoology, Faculty of Life Sciences, Tel Aviv University; Tel Aviv, Israel.
  • School of Computer Science, Reichman University; Herzliya, Israel.
  • Sagol School of Neuroscience, Tel Aviv University; Tel Aviv, Israel.
  • Edmond J. Safra Center for Bioinformatics, Tel Aviv University; Tel Aviv, Israel.

ORCID-Profile: Yoav Ram

Förderung

  • Israel science foundation
  • Minerva Foundation
  • Amazon Web Services
  • Nvidia

Zitieren

APA

Shvartzman, B., & Ram, Y. (2024). Self-replicating artificial neural networks give rise to universal evolutionary dynamics. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012004

Vancouver

Shvartzman B, Ram Y. Self-replicating artificial neural networks give rise to universal evolutionary dynamics. PLOS Computational Biology. 2024. doi:10.1371/journal.pcbi.1012004

BibTeX
@article{Shvartzman2024,
  author = {Shvartzman, Boaz and Ram, Yoav},
  title = {Self-replicating artificial neural networks give rise to universal evolutionary dynamics},
  journal = {PLOS Computational Biology},
  year = {2024},
  doi = {10.1371/journal.pcbi.1012004}
}
Kostenlos starten →