ODE2VAE: Deep generative second order ODEs with Bayesian neural networks

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

6 Sitaatiot (Scopus)

Abstrakti

We present Ordinary Differential Equation Variational Auto-Encoder (ODE2VAE), a latent second order ODE model for high-dimensional sequential data. Leveraging the advances in deep generative models, ODE2VAE 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.
AlkuperäiskieliEnglanti
Otsikko33rd Conference on Neural Information Processing Systems
AlaotsikkoNeurIPS 2019
KustantajaNeural Information Processing Systems Foundation
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaConference on Neural Information Processing Systems - Vancouver, Kanada
Kesto: 8 joulukuuta 201914 joulukuuta 2019
Konferenssinumero: 33
https://neurips.cc

Julkaisusarja

NimiAdvances in Neural Information Processing Systems
KustantajaNeural Information Processing Systems Foundation
Vuosikerta32
ISSN (elektroninen)1049-5258

Conference

ConferenceConference on Neural Information Processing Systems
LyhennettäNeurIPS
MaaKanada
KaupunkiVancouver
Ajanjakso08/12/201914/12/2019
www-osoite

Sormenjälki Sukella tutkimusaiheisiin 'ODE2VAE: Deep generative second order ODEs with Bayesian neural networks'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä