MARBLE: interpretable representations of neural population dynamics using geometric deep learning.

ABSTRACT: The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations. We introduce a representation learning method, MARBLE, which decomposes on-manifold dynamics into local flow fields and maps them into a common latent space using unsupervised geometric deep learning. In simulated nonlinear dynamical systems, recurrent neural networks and experimental single-neuron recordings from primates and rodents, we discover emergent low-dimensional latent representations that parametrize high-dimensional neural dynamics during gain modulation, decision-making and changes in the internal state. These representations are consistent across neural netw

SUBMITTER: Gosztolai A 

PROVIDER: S-EPMC11903309 | biostudies-literature | 2025 Mar

REPOSITORIES: biostudies-literature