Research map / Probabilistic and scientific modeling / Variational and generative sampling
Approximation Capabilities of Neural ODEs and Invertible Residual Networks
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 |
|---|---|---|---|
| Add one dimension to the input and output for the negation mapping | i-ResNet · Synthetic negation test set | MSE: 33.39 -> below $10^{-10}$ | Helped |
| Add null channels to CIFAR10 inputs, increasing dimensionality up to 3 additional channels (ablation) | Neural ODE with 64 or more convolutional filters · CIFAR10 test set | cross-entropy loss | Helped |
| Add null channels beyond 3 additional channels (ablation) | Neural ODE with 64 or more convolutional filters · CIFAR10 test set | cross-entropy loss: $p$=.002 | Mixed |
| Increase the number of convolutional filters to 64 or more (ablation) | Neural ODE · CIFAR10 test set | cross-entropy loss | Mixed |
Closest papers by meaning
- Do Residual Neural Networks discretize Neural Ordinary Differential Equations? (NeurIPS 2022 · similarity 0.89)
- Learning Efficient and Robust Ordinary Differential Equations via Invertible Neural Networks (ICML 2022 · similarity 0.88)
- ANODEV2: A Coupled Neural ODE Framework (NeurIPS 2019 · similarity 0.88)
- Implicit regularization of deep residual networks towards neural ODEs (ICLR 2024 · similarity 0.87)
- Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure (AAAI 2025 · similarity 0.86)
- Characterizing ResNet's Universal Approximation Capability (ICML 2024 · similarity 0.86)
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.