Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Neural Ordinary Differential Equations
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| replace residual blocks with ODE solver block (ODE-Net) | small ResNet · MNIST | test error: 0.41% -> 0.42% | No clear effect |
| replace residual blocks with ODE solver block | small ResNet · MNIST | # params: 0.60 M -> 0.22 M | Helped |
| adjoint method instead of backprop through Runge-Kutta integrator | ODE-Net · MNIST | memory | Helped |
| latent ODE instead of RNN for irregular time series | time-series model · Bi-directional spiral 30/100 obs | predictive RMSE: 0.3937 -> 0.1642 | Helped |
| continuous normalizing flow instead of planar NF | normalizing flows · density matching toy | KL loss | Helped |
| lower ODE solver tolerance (ablation) | ODE-Net · MNIST | number of function evaluations | Mixed |
Closest papers by meaning
- Do Residual Neural Networks discretize Neural Ordinary Differential Equations? (NeurIPS 2022 · similarity 0.92)
- Sparse Flows: Pruning Continuous-depth Models (NeurIPS 2021 · similarity 0.92)
- Efficient Continuous-Depth Modeling with GRU Equivalents (ICML 2026 · similarity 0.92)
- Implicit regularization of deep residual networks towards neural ODEs (ICLR 2024 · similarity 0.91)
- Simulation-Free Training of Neural ODEs on Paired Data (NeurIPS 2024 · similarity 0.90)
- Improving Neural ODE Training with Temporal Adaptive Batch Normalization (NeurIPS 2024 · similarity 0.90)
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.