AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Stateful ODE-Nets using Basis Function Expansions

Alejandro Francisco Queiruga, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Weight normalization and decay interplay · 2 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
add continuous-in-depth batch normalization (ablation)Stateful ODE-Net · MNISTaverage accuracy: 99.1% -> 99.4%Improved
add continuous-in-depth batch normalization (ablation)Stateful ODE-Net · CIFAR-10 shallowaverage accuracy: 88.4% -> 90.4%Improved
add continuous-in-depth batch normalization (ablation)Stateful ODE-Net · CIFAR-10 deepaverage accuracy: 10.0% -> 92.4%Improved
compress by reducing basis functions and timesteps 8 to 4Stateful ODE-Net · MNISTaverage accuracy: 99.4% -> 99.2%No clear effect
compress further to 7K parametersStateful ODE-Net · MNISTaverage accuracy: 99.4% -> 96.9%Hurt
compress basis functions 8 to 4Stateful ODE-Net · CIFAR-10 shallowaverage accuracy: 90.4% -> 89.9%No clear effect
compress model trained with refinement training (c1)Stateful ODE-Net · CIFAR-10 deepaverage accuracy: 92.4% -> 91.8%No clear effect
compress model trained without refinement training (c2)Stateful ODE-Net · CIFAR-10 deepaverage accuracy: 94.1% -> 60.5%Hurt
train with refinement training and piecewise linear basis (c1 vs c2)Stateful ODE-Net · CIFAR-10 deepaverage accuracy: 94.1% -> 92.4%Hurt
refinement training (c1) on CIFAR-100Stateful ODE-Net · CIFAR-100average accuracy: 79.1% -> 76.9%Hurt
compress c2 on CIFAR-100Stateful ODE-Net · CIFAR-100average accuracy: 79.1% -> 48.9%Hurt
compress c1 on CIFAR-100Stateful ODE-Net · CIFAR-100average accuracy: 76.9% -> 75.6%No clear effect

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