ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1905.10994
11
88

ODE2^22VAE: Deep generative second order ODEs with Bayesian neural networks

27 May 2019
Çağatay Yıldız
Markus Heinonen
Harri Lähdesmäki
    BDL
    DRL
ArXivPDFHTML
Abstract

We present Ordinary Differential Equation Variational Auto-Encoder (ODE2^22VAE), a latent second order ODE model for high-dimensional sequential data. Leveraging the advances in deep generative models, ODE2^22VAE can simultaneously learn the embedding of high dimensional trajectories and infer arbitrarily complex continuous-time latent dynamics. Our model explicitly decomposes the latent space into momentum and position components and solves a second order ODE system, which is in contrast to recurrent neural network (RNN) based time series models and recently proposed black-box ODE techniques. In order to account for uncertainty, we propose probabilistic latent ODE dynamics parameterized by deep Bayesian neural networks. We demonstrate our approach on motion capture, image rotation and bouncing balls datasets. We achieve state-of-the-art performance in long term motion prediction and imputation tasks.

View on arXiv
Comments on this paper