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

05/27/2019
by   Çağatay Yıldız, et al.
0

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 non-parametric 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.

READ FULL TEXT
research
08/10/2021

Analysis of ODE2VAE with Examples

Deep generative models aim to learn underlying distributions that genera...
research
11/08/2020

Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations

Many real-world systems, such as moving planets, can be considered as mu...
research
12/09/2019

InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers

Continuous Normalizing Flows (CNFs) have emerged as promising deep gener...
research
02/24/2016

Learning to Generate with Memory

Memory units have been widely used to enrich the capabilities of deep ne...
research
09/29/2018

Auto-conditioned Recurrent Mixture Density Networks for Complex Trajectory Generation

Recent advancements in machine learning research have given rise to recu...
research
06/11/2020

Learning Continuous-Time Dynamics by Stochastic Differential Networks

Learning continuous-time stochastic dynamics from sparse or irregular ob...
research
08/04/2021

Spacetime Neural Network for High Dimensional Quantum Dynamics

We develop a spacetime neural network method with second order optimizat...

Please sign up or login with your details

Forgot password? Click here to reset