EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Encoding innate ability through a genomic bottleneck

Sergey Shuvaev iD, Divyansha Lachi, Alexei Koulakov, Anthony Zador

Proceedings of the National Academy of Sciences · 2024

DOI: 10.1073/pnas.2409160121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, 2024. Verfasst von Sergey Shuvaev und 3 weiteren Autor:innen. Beteiligte Einrichtung: Cold Spring Harbor Laboratory, Cold Spring Harbor, NY 11724. Hauptthemen laut MEDLINE: Neural Networks, Computer, Algorithms. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Schmidt Futures, G. Harold and Leila Y. Mathers Foundation (Mathers Foundation), Eleanor Schwartz Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Animals are born with extensive innate behavioral capabilities, which arise from neural circuits encoded in the genome. However, the information capacity of the genome is orders of magnitude smaller than that needed to specify the connectivity of an arbitrary brain circuit, indicating that the rules encoding circuit formation must fit through a “genomic bottleneck” as they pass from one generation to the next. Here, we formulate the problem of innate behavioral capacity in the context of artificial neural networks in terms of lossy compression of the weight matrix. We find that several standard network architectures can be compressed by several orders of magnitude, yielding pretraining performance that can approach that of the fully trained network. Interestingly, for complex but not for simple test problems, the genomic bottleneck algorithm also captures essential features of the circuit, leading to enhanced transfer learning to novel tasks and datasets. Our results suggest that compressing a neural circuit through the genomic bottleneck serves as a regularizer, enabling evolution to select simple circuits that can be readily adapted to important real-world tasks. The genomic bottleneck also suggests how innate priors can complement conventional approaches to learning in designing algorithms for AI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAlgorithmsAnimalsGenomicsGenomeHumans

Stichwörter der Autor:innen

AImachine learningneural computationneural networks

Autor:innen und Institutionen

  • Cold Spring Harbor Laboratory, Cold Spring Harbor, NY 11724.

ORCID-Profile: Sergey Shuvaev

Förderung

  • Schmidt Futures
  • G. Harold and Leila Y. Mathers Foundation (Mathers Foundation)
  • Eleanor Schwartz Foundation

Zitieren

APA

Shuvaev, S., Lachi, D., Koulakov, A., & Zador, A. (2024). Encoding innate ability through a genomic bottleneck. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2409160121

Vancouver

Shuvaev S, Lachi D, Koulakov A, Zador A. Encoding innate ability through a genomic bottleneck. Proceedings of the National Academy of Sciences. 2024. doi:10.1073/pnas.2409160121

BibTeX
@article{Shuvaev2024,
  author = {Shuvaev, Sergey and Lachi, Divyansha and Koulakov, Alexei and Zador, Anthony},
  title = {Encoding innate ability through a genomic bottleneck},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2024},
  doi = {10.1073/pnas.2409160121}
}
Kostenlos starten →