AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

ODE2VAE: Deep generative second order ODEs with Bayesian neural networks

Cagatay Yildiz, Markus Heinonen, Harri Lahdesmaki

NeurIPS 2019 · Probabilistic and scientific modeling › Dynamical systems · approach: Physics-informed dynamics learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add KL penalty between encoder and ODE-flow distributions (ODE2VAE-KL vs ODE2VAE) (ablation)ODE2VAE · CMU Mocap-1MSE on future frames: 93.07 -> 15.99Improved
add KL penalty between encoder and ODE-flow distributions (ablation)ODE2VAE · CMU Mocap-2MSE on future frames: 10.06 -> 8.09Improved
add KL penalty between encoder and ODE-flow distributions (ablation)ODE2VAE · Rotating MNIST test angleprediction error: 0.0194 -> 0.0188Improved
second-order Bayesian latent ODE instead of first-order deterministic Neural ODElatent ODE VAE · CMU Mocap-1MSE on future frames: 87.23 -> 15.99Improved
second-order Bayesian latent ODE instead of first-order deterministic Neural ODElatent ODE VAE · CMU Mocap-2MSE on future frames: 22.49 -> 8.09Improved
continuous-time ODE latent dynamics instead of RNN-based DTSBN-Sdeep generative sequence model · CMU Mocap-1MSE on future frames: 80.21 -> 15.99Improved
plain ODE2VAE vs black-box npODE on small datasetODE2VAE · CMU Mocap-1MSE on future frames: 45.74 -> 93.07Hurt
ODE2VAE-KL vs GPPVAE-joint on rotating MNISTODE2VAE-KL · Rotating MNIST test angleprediction error: 0.0288 -> 0.0188Improved
CNN encoder on channel-stacked frames instead of RNN encoder (ablation)ODE2VAE · Bouncing ballsprediction MSEImproved
ODE2VAE vs DDPAE and DTSBN-S on bouncing ballsODE2VAE · Bouncing ballsper-pixel MSE on 10 future framesImproved
larger second dataset (Mocap-2) vs smaller (Mocap-1)all models · CMU MocapMSE on future frames: 93.07 -> 10.06Improved

Later papers that compared with this method

3 later accepted papers report ODE2VAE as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy