AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Noether Networks: meta-learning useful conserved quantities

Ferran Alet, Dylan Doblar, Allan Zhou, Joshua B. Tenenbaum, Kenji Kawaguchi, Chelsea Finn

NeurIPS 2021 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations · 6 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
Meta-tailor the predictor with a synthesized conservation formulaVanilla MLP · Ideal pendulumRMSE: 0.0563 -> 0.0423Improved
Meta-tailor the predictor with a synthesized conservation formulaVanilla MLP · Ideal springRMSE: .0174 -> .0165Improved
Use an automatically discovered conservation formula instead of the true formulaNoether Nets · Ideal pendulumRMSE: 0.0423 vs 0.0422No clear effect
Use an automatically discovered conservation formula instead of the true formulaNoether Nets · Ideal springRMSE: .0165 vs .0166No clear effect
Add prediction-time tailoring with a learned conserved quantitySVG · Controlled pixel pendulumMSEImproved
Add prediction-time tailoring with a learned conserved quantitySVG · Physics 101 ramp, 20-degree inclineLPIPSImproved
Add prediction-time tailoring with a learned conserved quantitySVG · Physics 101 ramp, 20-degree inclineMSEImproved
Add prediction-time tailoring with a learned conserved quantitySVG · Physics 101 ramp, 20-degree inclinePSNRImproved
Add prediction-time tailoring with a learned conserved quantitySVG · Physics 101 ramp, 20-degree inclineSSIMImproved
Continue training SVG for 20 additional epochs instead of adding Noether tailoringSVG · Controlled pixel pendulumMSENo clear effect
Increase the number of inner conservation-optimization stepsNoether Networks · Physics 101 ramp, 20-degree inclineTask lossImproved

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