Self-supervised predictive learning accounts for cortical layer-specificity.

ABSTRACT: The neocortex constructs an internal representation of the world, but the underlying circuitry and computational principles remain unclear. Inspired by self-supervised learning algorithms, we propose a computational theory in which layer 2/3 (L2/3) integrates past sensory input, relayed via layer 4, with top-down context to predict incoming sensory stimuli. Learning is self-supervised by comparing L2/3 predictions with the latent representations of actual sensory input arriving at L5. We demonstrate that our model accurately predicts sensory information in context-dependent temporal tasks, and that its predictions are robust to noisy and occluded sensory input. Additionally, our model generates layer-specific sparsity, consistent with experimental observations. Next, using a sensorimotor t

SUBMITTER: Nejad KK 

PROVIDER: S-EPMC12227776 | biostudies-literature | 2025 Jul

REPOSITORIES: biostudies-literature