Research map / Probabilistic and scientific modeling / Differential equations and PDEs
On Second Order Behaviour in Augmented Neural ODEs
Alexander Norcliffe, Cristian Bodnar, Ben Day, Nikola Simidjievski, Pietro Lió
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use second order SONODE instead of NODE | Neural ODE · Generalised parity problem | loss | Improved |
| add augmented dimensions (ANODE) to NODE | Neural ODE · Generalised parity problem | loss | Improved |
| use SONODE instead of ANODE | Augmented Neural ODE · Generalised parity problem | loss | Improved |
| use SONODE instead of ANODE | Augmented Neural ODE · Damped harmonic oscillator | training iterations to converge | Improved |
| use SONODE instead of ANODE | Augmented Neural ODE · Sine curve with noise | extrapolation error | Improved |
| use SONODE instead of ANODE(1) | Augmented Neural ODE · Silverbox oscillator | loss and extrapolation | Improved |
| use SONODE instead of ANODE(1) | Augmented Neural ODE · Airplane vibrations | extrapolation error | Hurt |
| use first order coupled ODE adjoint instead of second order adjoint | SONODE training · SONODE gradient computation | matrix multiplications | Improved |
| use SONODE instead of ANODE(2) for recovering velocity | Augmented Neural ODE · 2D second order ODE | recovered true velocity | Improved |
Closest papers by meaning
- ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence (NeurIPS 2024 · similarity 0.91)
- How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective (ICML 2024 · similarity 0.89)
- Semi-Implicit Neural Ordinary Differential Equations (AAAI 2025 · similarity 0.89)
- Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach (AAAI 2024 · similarity 0.88)
- Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure (AAAI 2025 · similarity 0.88)
- SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases (ICLR 2024 · similarity 0.87)
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.
