Timezone: »

 
Poster
ODE2VAE: Deep generative second order ODEs with Bayesian neural networks
Cagatay Yildiz · Markus Heinonen · Harri Lahdesmaki

Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #148
in Deep Learning -- Generative Models »

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.

Keywords: Generative Models · Latent Variable Models · Deep Learning · Probabilistic Methods

Author Information

Cagatay Yildiz (Aalto University)
Markus Heinonen (Aalto University)
Harri Lahdesmaki (Aalto University)

More from the Same Authors