EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The curriculum effect in visual learning: The role of readout dimensionality

Charlotte Volk iD, Christopher C Pack, Shahab Bakhtiari iD

PLOS Computational Biology · 24.07.2026 · 22 (7) · e1014553

DOI: 10.1371/journal.pcbi.1014553 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 24.07.2026. Verfasst von Charlotte Volk und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, McGill University, Montréal, QC, Canada. Hauptthemen laut MEDLINE: Learning, Visual Perception. Die Arbeit nennt 93 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, IVADO.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generalization of visual perceptual learning (VPL) to unseen conditions varies across tasks. Previous work suggests that training curriculum may be integral to generalization, yet a theoretical explanation is lacking. We propose an explanatory theory of visual learning generalization and curriculum effects by leveraging an artificial neural network (ANN) model of VPL in comparison with humans. We found that easy-to-hard sequential training improved generalization in both humans and ANNs. However, when easy and hard conditions were interleaved, humans and ANNs showed different behaviours: while ANNs performed worse than with sequential training, humans maintained good performance but with large inter-individual variability. Investigating ANN models trained with different curricula, we demonstrated that models relying on low-dimensional neural populations showed superior generalization. This readout subspace dimensionality was directly determined by curriculum: learners who learned from easy tasks early formed lower-dimensional subspaces and generalized better. Our theory provides a mechanistic framework linking curriculum design to VPL generalization through neural population dimensionality.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LearningVisual PerceptionHumansNeural Networks, ComputerCurriculumComputational BiologyModels, NeurologicalGeneralization, Psychological

Autor:innen und Institutionen

  • School of Computer Science, McGill University, Montréal, QC, Canada.
  • Mila - Quebec AI Institute, Montréal, QC, Canada.
  • Department of Neurology & Neurosurgery, McGill University, Montréal, QC, Canada.
  • Montreal Neurological Institute, Montréal, QC, Canada.
  • Department of Psychology, Université de Montréal, Montréal, QC, Canada.

ORCID-Profile: Charlotte Volk, Shahab Bakhtiari

Förderung

  • Natural Sciences and Engineering Research Council of Canada
  • IVADO

Zitieren

APA

Volk, C., Pack, C. C., & Bakhtiari, S. (2026). The curriculum effect in visual learning: The role of readout dimensionality. PLOS Computational Biology, 22(7), e1014553. https://doi.org/10.1371/journal.pcbi.1014553

Vancouver

Volk C, Pack CC, Bakhtiari S. The curriculum effect in visual learning: The role of readout dimensionality. PLOS Computational Biology. 2026;22(7):e1014553. doi:10.1371/journal.pcbi.1014553

BibTeX
@article{Volk2026,
  author = {Volk, Charlotte and Pack, Christopher C and Bakhtiari, Shahab},
  title = {The curriculum effect in visual learning: The role of readout dimensionality},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {7},
  pages = {e1014553},
  doi = {10.1371/journal.pcbi.1014553}
}
Kostenlos starten →