EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Manifold-constrained plasticity enables stable learning in recurrent neural circuits

Camille Godin, Jean-Philippe Thivierge

PLOS Computational Biology · 2026

DOI: 10.1371/journal.pcbi.1014719 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2026. Verfasst von Camille Godin und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Psychology, University of Ottawa, Ottawa, Canada. Hauptthemen laut MEDLINE: Neuronal Plasticity, Models, Neurological, Learning, Nerve Net. Die Arbeit nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada (NSERC), natural sciences and engineering council of canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The activity of large neuronal populations is often confined to low-dimensional manifolds that can drift over time, posing a challenge for learning rules that assume stable, full-rank representations. Here, we introduce SPLiT (Synaptic Projection Learning with intrinsic Tracking), a synaptic plasticity rule for recurrent neural networks that combines unsupervised manifold tracking with supervised learning. SPLiT uses an online Oja rule to continuously estimate the intrinsic low-dimensional activity subspace and performs normalized least-mean-squares learning in manifold coordinates. In this way, SPLiT keeps synaptic weights aligned with evolving population dynamics. Using a rate-based recurrent network, we show that SPLiT reliably learns time-varying target signals under both constrained dynamics, where activity is restricted to a fixed low-dimensional manifold, and unconstrained dynamics exhibiting changes in the dominant activity subspace. We show that manifold-constrained learning with SPLiT yields faster convergence, less sensitivity to recurrent gain, smaller weight updates, and is more robust to noisy teaching signals. Analytical results show that SPLiT learns the optimal decoder projected onto the instantaneous principal subspace and maintains bounded error under drift. Together, these findings provide a mechanistic account of how synaptic plasticity can leverage the structure of neural manifolds to enable stable and efficient supervised learning despite representational drift.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neuronal PlasticityModels, NeurologicalLearningNerve NetNeural Networks, ComputerRecurrent Neural NetworksAnimalsComputational BiologyAlgorithmsNeuronsHumans

Autor:innen und Institutionen

  • School of Psychology, University of Ottawa, Ottawa, Canada.
  • Brain and Mind Research Institute, University of Ottawa, Ottawa, Canada.

Förderung

  • Natural Sciences and Engineering Research Council of Canada (NSERC)
  • natural sciences and engineering council of canada

Zitieren

APA

Godin, C., & Thivierge, J. P. (2026). Manifold-constrained plasticity enables stable learning in recurrent neural circuits. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1014719

Vancouver

Godin C, Thivierge JP. Manifold-constrained plasticity enables stable learning in recurrent neural circuits. PLOS Computational Biology. 2026. doi:10.1371/journal.pcbi.1014719

BibTeX
@article{Godin2026,
  author = {Godin, Camille and Thivierge, Jean-Philippe},
  title = {Manifold-constrained plasticity enables stable learning in recurrent neural circuits},
  journal = {PLOS Computational Biology},
  year = {2026},
  doi = {10.1371/journal.pcbi.1014719}
}
Kostenlos starten →