AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Integral Autoencoder Network for Discretization-Invariant Learning

Yong Zheng Ong, Zuowei Shen, Haizhao Yang

JMLR 2022 · Architectures and efficiency › RNNs and normalization · approach: Sparse dictionary representations

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
use IAE-Net instead of dgFNO+Darcy problem in notched triangular domain · Darcy problem, triangular domain with notch (s=50)L2 relative error (%): 7.821% -> 0.8094%Improved
use IAE-Net instead of POD-DeepONetDarcy problem in notched triangular domain · Darcy problem, triangular domain with notch (s=50)L2 relative error (%): 1.00% -> 0.8094%Improved
test IAE-Net at higher resolutions than trainedIAE-Net · Darcy problem, triangular domain with notchL2 relative error (%): 0.8094% -> 0.8317%No clear effect
add randomized data augmentation across resolutions to IAE-Net (ablation)IAE-Net · Burgers equation benchmark (nu=1e-1)L2 relative error across resolutionsImproved
use dense skip connections instead of ResNet skip connections in IAE-Net (ablation)IAE-Net · Burgers equation benchmarkL2 relative error: almost 2 times better than the ResNet counterpartImproved
use ResNet skip connections instead of dense connections in IAE-Net (ablation)IAE-Net · Darcy benchmarkL2 relative errorHurt
use multiple IAE blocks (4) instead of one block with deeper networks (ablation)IAE-Net · Burgers equation benchmark (s=1024)L2 relative error: reducing error by 2 timesImproved
increase number of IAE blocks to L=5 (ablation)IAE-Net · Burgers equation benchmark (s=1024)L2 relative errorMixed
use IAE-Net instead of FNO, FT and GTBurgers equation (nu=1e-1) · Burgers equationL2 relative error: almost 3 times betterImproved
use IAE-Net instead of FNO, FT and GTscattering problem · Scattering forward and inverseL2 relative error: more than 10 times higher error for baselinesImproved
use IAE-Net instead of FNO, FT and GTCT image denoising · CT denoising (30 view, 5% noise)L2 relative error: about 3 times lower errorImproved
train on resolutions sequentially instead of jointly with summed gradients (ablation)IAE-Net · Scattering, mixed resolutionstest errorHurt

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