AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks

Sifan Wang, Bowen Li, Yuhan Chen, Paris Perdikaris

JMLR 2024 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training · 85 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
Initialize adaptive residual parameter alpha to 0 instead of 1 (ablation)PirateNet · Grey-Scottrelative L2 error: one or two orders of magnitude lower errorImproved
Initialize adaptive residual parameter alpha to 0 instead of 1 (ablation)PirateNet · Ginzburg-Landaurelative L2 error: alpha=1 gives complete model collapse for deeper networksImproved
Add gating operations to PirateNet blocks (ablation)PirateNet · Grey-Scottrelative L2 errorImproved
Add gating operations to PirateNet blocks (ablation)PirateNet · Ginzburg-Landaurelative L2 errorImproved
Increase depth of PirateNet (ablation)PirateNet · Allen-Cahnrelative L2 error: consistent improvement in accuracy as depth increasesImproved
Increase depth of Modified MLP (ablation)Modified MLP · Allen-Cahnrelative L2 error: increasing error in deeper networksHurt
Increase depth of MLP (ablation)MLP PINN · Allen-Cahnrelative L2 error: almost 100% error at 18 hidden layersHurt
Add residual connections to MLP (ablation)MLP PINN · Allen-Cahnrelative L2 errorNo clear effect
Add physics-informed least-squares initialization of the last layer (ablation)Modified MLP and PirateNet · Allen-Cahnrelative L2 errorImproved
Fit linearized PDE solution instead of initial condition for initialization (ablation)PirateNet · Allen-Cahnrelative L2 errorNo clear effect
Use PirateNet instead of Modified MLP backbone without physics-informed initialization (ablation)PirateNet · Korteweg-De Vriesrelative L2 errorImproved
Increase PirateNet depth beyond 20 layers (ablation)PirateNet · Lid-driven cavity flow (Re=3200)relative L2 error: saturates beyond depth 20, similar to depth 18No 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