EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Invariant visual object and face learning in the ventral cortical visual pathway: A biologically plausible model

Chenfei Zhang, Edmund T Rolls iD, Jianfeng Feng

PLOS Computational Biology · 2026

DOI: 10.1371/journal.pcbi.1013959 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Chenfei Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute for the Science and Technology of Brain-Inspired Intelligence, Fudan University, Shanghai, China. Hauptthemen laut MEDLINE: Visual Cortex, Models, Neurological, Learning, Visual Pathways. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 110 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Project 111.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

How transform-invariant visual representations of objects and faces are learned in the ventral visual cortical pathway is a massive computational problem. Here we describe key advances towards a biologically plausible four-layer network that performs these computations from the primary visual cortex to the inferior temporal visual cortex. The architecture is a four-layer competitive network with layer-to-layer convergence using a short-term memory trace local synaptic learning rule to associate transforming inputs from an object during natural viewing. The key advances towards biological plausibility include: (1) a synaptic modification rule including long-term depression dependent on synaptic strength instead of artificial synaptic weight normalization; (2) limiting the strength of synapses promotes distributed weights, improving transform-invariant learning; (3) reducing the ability of low firing rate neurons to participate in learning analogous to the NMDA receptor non-linearity can increase the storage capacity; (4) demonstrated network scalability towards high capacity. These advances have many implications for better understanding of cortical computations. These advances in biological plausibility of this approach are compared with artificial networks of the same ventral cortical processing stream that do not use a local synaptic learning rule and are less biologically plausible, and implications for AI models are described.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Visual CortexModels, NeurologicalLearningVisual PathwaysHumansAnimalsSynapsesFaceComputational BiologyComputer SimulationNeurons

Autor:innen und Institutionen

  • Institute for the Science and Technology of Brain-Inspired Intelligence, Fudan University, Shanghai, China.
  • Oxford Centre for Computational Neuroscience, Oxford, United Kingdom.
  • University of Warwick, Department of Computer Science, Coventry, United Kingdom.

ORCID-Profile: Edmund T Rolls

Förderung

  • Project 111

Zitieren

APA

Zhang, C., Rolls, E. T., & Feng, J. (2026). Invariant visual object and face learning in the ventral cortical visual pathway: A biologically plausible model. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013959

Vancouver

Zhang C, Rolls ET, Feng J. Invariant visual object and face learning in the ventral cortical visual pathway: A biologically plausible model. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1013959

BibTeX
@article{Zhang2026,
  author = {Zhang, Chenfei and Rolls, Edmund T and Feng, Jianfeng},
  title = {Invariant visual object and face learning in the ventral cortical visual pathway: A biologically plausible model},
  journal = {PLOS Computational Biology},
  year = {2026},
  doi = {10.1371/journal.pcbi.1013959}
}
Kostenlos starten →