Skip to main content
Search

# Neural Ordinary Differential Equation

5 related articles

Subscribe to updates
  1. bioRxiv

    Where cognitive-state information lives depends on brain-dynamics complexity: working memory rides trajectories, relational reasoning rides time averages

    A single learned model of brain dynamics yields both a time-averaged connectivity representation and a trajectory-geometry representation, and which one carries condition-discriminative information shifts with chronnectome complexity. On eight conditions in the Human Connectome Project young adult cohort, the full model reached 97.4% classification accuracy; with the time-averaged representation zeroed out, trajectory-only accuracy ranged from 93.4% for Working Memory to 0.0% for Relational Reasoning, the latter indistinguishable from a label-permutation null. In the aging cohort's four conditions, the time-averaged representation carried most of the discriminative information, yet the contrast between higher- and lower-complexity conditions persisted.

  2. bioRxiv

    DynISys splits multi-area recordings into per-area dynamics, with PMd-to-M1 traffic confined to three dimensions

    Separating a brain area's own dynamics from the inputs driving it is hard, because the same recorded activity can arise from many combinations of the two. DynISys models each recorded area as its own low-dimensional dynamical system, lets areas exchange signals only through a few explicit channels, and maps latent states to firing rates through an invertible readout. On simultaneous PMd and M1 recordings from two monkeys, eight latent dimensions per area matched the PSTH reconstruction of MR-LFADS at 128 per area, and the inferred PMd-to-M1 communication timing was consistent with target information traveling from PMd to M1.

  3. arXiv

    Robot policies learn action dynamics instead of actions: ODE Policy hits 79.2% on LIBERO after one epoch, versus 43.2% at best for baselines

    Most robot policies output action values at discrete control steps and leave the continuity of physical motion to be learned implicitly from data. ODE Policy instead learns a neural ordinary differential equation for the vector field of the action, and at deployment integrates each action from the previous one, so the executed trajectory is continuous by construction. After one epoch on LIBERO it reaches 79.2% success against at most 43.2% for the baselines, and it keeps that early lead as the action head of a VLA and of ImageWAM and as the actor of SuperMimic.

  4. arXiv

    HyperNSDE writes static baselines into a neural SDE drift via a hypernetwork, improving observation-time fidelity on simulated and real clinical data

    The authors propose HyperNSDE, a continuous-time generative model that encodes heterogeneous static covariates with an HI-VAE, maps the static latent representation through a hypernetwork to subject-specific drift parameters driving a latent Neural SDE, and jointly models observation times with a latent-state-dependent intensity process, trained via a deterministic–stochastic path decomposition with a signature-kernel objective; on simulated data and the VELOUR and PPMI cohorts it achieves better observation-time fidelity and several distributional and privacy metrics, while forecasting and correlation performance is mixed and affected by observation-grid regularity and trajectory smoothness.

  5. An autoencoder plus neural ODE surrogate for ASTEC vessel physics compresses 1913 dimensions to 6 and cuts one simulation from about 4.7 hours to about 19 seconds

    Decoupling the ASTEC vessel physics (the CESAR-ICARE coupling), this work builds a surrogate that uses an autoencoder for dimensionality reduction and a neural ODE to advance time in latent space, training one model each on station blackout and loss-of-coolant accident data; it predicts about 80 scalar and field variables simultaneously, rolls out stably for 10k to 50k time steps (about 4 to 40 hours), compresses 1913 degrees of freedom to 6 latent dimensions (about 332x), and produces the full spatio-temporal prediction in under a minute on both CPU and GPU, with LOCA mean times of about 26.5 s on CPU and 18.9 s on GPU versus 16879.8 s for ASTEC's ICARE module alone, roughly a 640x speedup.

You’re all caught up