EUVIMEDEUVIMED entdecken
Crossref

Beyond learnability: understanding human visual development with DNNs

Lei Yuan

Trends in Cognitive Sciences · 2024

DOI: 10.1016/j.tics.2024.05.002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Trends in Cognitive Sciences, 2024. Verfasst von Lei Yuan. Beteiligte Einrichtung: Department of Psychology and Neuroscience, University of Colorado Boulder, Boulder, CO, USA. Electronic address: lei.yuan@colorado.edu. Hauptthemen laut MEDLINE: Learning, Visual Perception. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 10 Literaturangaben. Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, Orhan and Lake demonstrated the computational plausibility that children can acquire sophisticated visual representations from natural input data without inherent biases, challenging the need for innate constraints in human learning. The findings may also reveal crucial properties of early visual learning and inform theories of human visual development.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LearningVisual PerceptionChildHumansChild DevelopmentNeural Networks, Computer

Stichwörter der Autor:innen

developmentintelligencelearningmachine learningvision

Autor:innen und Institutionen

  • Department of Psychology and Neuroscience, University of Colorado Boulder, Boulder, CO, USA. Electronic address: lei.yuan@colorado.edu.

Förderung

  • National Science Foundation

Zitieren

APA

Yuan, L. (2024). Beyond learnability: understanding human visual development with DNNs. Trends in Cognitive Sciences. https://doi.org/10.1016/j.tics.2024.05.002

Vancouver

Yuan L. Beyond learnability: understanding human visual development with DNNs. Trends in Cognitive Sciences. 2024. doi:10.1016/j.tics.2024.05.002

BibTeX
@article{Yuan2024,
  author = {Yuan, Lei},
  title = {Beyond learnability: understanding human visual development with DNNs},
  journal = {Trends in Cognitive Sciences},
  year = {2024},
  doi = {10.1016/j.tics.2024.05.002}
}
Kostenlos starten →