ODE2VAE: Deep generative second order ODEs with Bayesian neural networks

Cagatay YildizMarkus HeinonenHarri Lahdesmaki

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... (read more)

PDF Abstract