AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features

Thomas M. McDonald, Mauricio A Álvarez

NeurIPS 2021 · Probabilistic and scientific modeling › Dynamical systems · approach: State-space inference for stochastic systems · 1 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
Replace EQ random features with ODE-based random features in the deep modelDLFM versus DGP-EQ · CHARIS extrapolation, ABP and ECGNMSE: 0.73 -> 0.39; 0.66 -> 0.45Improved
Replace EQ random features with ODE-based random features in the deep modelDLFM versus DGP-EQ · CHARIS extrapolation, ABP and ECGMNLL: 1.21 -> 0.75; 1.22 -> 0.99Improved
Use two latent forces instead of one (ablation)DLFM · CHARIS extrapolation, ABP, ECG, and ICPNMSE: ABP: 0.39 -> 0.42; ECG: 0.45 -> 1.58; ICP: 0.36 -> 0.32Mixed
Use one latent force instead of two (ablation)DLFM · CHARIS extrapolation, ABP and ECGMNLL: ABP: 0.77 -> 0.75; ECG: 1.16 -> 0.99Improved
Use two latent forces instead of one (ablation)DLFM · CHARIS extrapolation, ICPMNLL: 0.90 -> 0.88Improved
Use ODE-based random features rather than EQ random featuresDLFM versus DGP-EQ · Powerplant testNMSE: 0.0581 -> 0.0557Improved
Use ODE-based random features rather than EQ random featuresDLFM versus DGP-EQ · Powerplant testMNLL: 0.016 -> - 0.017Improved
Use ODE-based random features rather than EQ random featuresDLFM versus DGP-EQ · Protein testMNLL: 1.101 -> 0.754Improved
Use the DLFM rather than DGP-EQDLFM · Protein testNMSE: 0.553 -> 0.698Hurt
Use the DLFM rather than DGP-EQDLFM · Toy system extrapolationMNLL: 3.7 -> 2.4Improved
Use the DLFM rather than C-DGPDLFM · FitzHugh-Nagumo, full-data fitNMSE: 0.01 -> 0.02Hurt
Use the DLFM rather than C-DGPDLFM · FitzHugh-Nagumo extrapolationNMSE: 0.38 -> 0.07Improved

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