Manifold-constrained plasticity enables stable learning in recurrent neural circuits
Open Access
- 25 August 2026
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22 (8) , e1014719
Abstract
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.Keywords
Funding Information
- Natural Sciences and Engineering Council of Canada (210977)
This publication has 72 references indexed in Scilit:
- Modeling and contractivity of neural-synaptic networks with Hebbian learningAutomatica, 2024
- Signatures of task learning in neural representationsCurrent Opinion in Neurobiology, 2023
- Unveiling the role of plasticity rules in reservoir computingNeurocomputing, 2021
- Dynamic Reorganization of Neuronal Activity Patterns in Parietal CortexCell, 2017
- Modeling neural plasticity in echo state networks for classification and regressionInformation Sciences, 2016
- The Errors of Our Ways: Understanding Error Representations in Cerebellar-Dependent Motor LearningThe Cerebellum, 2015
- On simplicity and complexity in the brave new world of large-scale neuroscienceCurrent Opinion in Neurobiology, 2015
- Neuronal Circuits Underlying Persistent Representations Despite Time Varying ActivityCurrent Biology, 2012
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009
- Simplified neuron model as a principal component analyzerJournal of Mathematical Biology, 1982