ODE^2VAE: Deep generative second order ODEs with Bayesian neural networks release_ajvxjvkf6ra6zbsvbkgipv2sqq

by Çağatay Yıldız, Markus Heinonen, Harri Lähdesmäki

Released as a article .

2019  

Abstract

We present Ordinary Differential Equation Variational Auto-Encoder (ODE^2VAE), a latent second order ODE model for high-dimensional sequential data. Leveraging the advances in deep generative models, ODE^2VAE 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.
In text/plain format

Archived Files and Locations

application/pdf  1.8 MB
file_5qpmehnkcrgcbko4vitveog7nu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-05-27
Version   v1
Language   en ?
arXiv  1905.10994v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 38cc5578-4814-4baf-a7dc-8054d07c72e1
API URL: JSON