AI Paper Atlas

Research map / Time series / Causal and generative time series

Neural ODE Processes

Alexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò

ICLR 2021 · Time series › Causal and generative time series · approach: Neural differential equations · 6 citations (OpenAlex)

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
use NDP instead of NP1D regression · SineMSE × 10^-2: 5.93 $\pm$ 0.96 -> 2.09 $\pm$ 0.12Improved
use NDP instead of NP1D regression · LinearMSE × 10^-2: 5.85 $\pm$ 0.70 -> 3.76 $\pm$ 0.32Improved
use NDP instead of NP1D regression · ExponentialMSE × 10^-2: 0.29 $\pm$ 0.03 -> 0.31 $\pm$ 0.08No clear effect
use NDP instead of NP1D regression · OscillatorsMSE × 10^-2: 0.64 $\pm$ 0.06 -> 0.72 $\pm$ 0.08No clear effect
use NDP instead of NPLotka-Volterra · Lotka-Volterratest MSE × 10^-2: 44 \pm 4 -> 15 \pm 2Improved
use NDP instead of NPCharacterTrajectories · CharacterTrajectoriestest MSE × 10^-1: 4.6 \pm 0.1 -> 3.4 \pm 0.1Improved
use NDP instead of NP on variable rotating digitsVariable Rotating MNIST · Variable Rotating MNISTqualitative prediction qualityImproved
use NDP instead of NP on constant-velocity rotating digitsRotating MNIST · Rotating MNISTqualitative prediction qualityNo clear effect
use second-order latent dynamics (ablation)NDP · SineMSE × 10^-2: 2.09 $\pm$ 0.12 -> 2.75 $\pm$ 0.19Hurt
use second-order latent dynamics (ablation)NDP · LinearMSE × 10^-2: 3.76 $\pm$ 0.32 -> 4.37 $\pm$ 1.14Hurt
use a linear latent-only decoder (ablation)NDP · SineMSE × 10^-2: 2.09 $\pm$ 0.12 -> 2.51 $\pm$ 0.24Hurt
set latent ODE dimension to 1 instead of 2 (ablation)NDP on Sine · SineMSE × 10^-2: 1.7 $\pm$ 0.1 -> 5.6 $\pm$ 1.3Hurt

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