AI Paper Atlas

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

Susceptibilities for Neural Networks Learning from Physical Data

Rohan Hitchcock, Gary W Delaney, Jonathan H Manton, Richard Scalzo, Jingge Zhu

NeurIPS 2026 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed neural network training · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes susceptibilities from statistical physics as a tool to analyse how a neural network trained on physical data responds to perturbations of physical parameters.

Problem

Neural networks trained on data from physical systems must learn regularities induced by underlying physical laws, and it is unclear how those laws shape the learning process.

Approach

Applies susceptibilities (response of a network to perturbations of a physical parameter of the data-generating system), a concept from statistical physics, as a framework for analysing learning from physical data.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
bias training mixture toward small lattice occupation probability h (alpha < 0) (ablation)15M transformer on percolating states, 16x16 lattice · percolation, h in [0.35, 0.6]mean maximum cluster height of generated samplesImproved
bias training mixture toward large h (alpha > 0) (ablation)15M transformer on percolating states · percolation, h in [0.35, 0.6]mean maximum cluster height of generated samplesHurt
restrict susceptibility to critical-site losses (masked susceptibility chi_crit) (ablation)susceptibility analysis · percolationpredictive value for data selectionImproved
use full susceptibility chi(h) instead of masked chi_crit(h) to guide data selection (ablation)susceptibility analysis · percolationinformativeness for data selectionNo clear effect
compare chi_crit with empirical loss, gradient norm and gradient dot product as diagnostics (ablation)data-selection diagnostics · percolationagreement with retraining resultNo clear effect
restrict susceptibility to attention-head parameters (chi_heads) instead of full-model loss (chi_full) (ablation)granular-material transformer · granular materials, psi = total collision forcedetection of collision-resolution emergenceImproved

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