AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Equilibrium Propagation for Non-Conservative Systems

Antonino Emanuele Scurria, Dimitri Vanden Abeele, Bortolo Matteo Mognetti, Serge Massar

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Switching and law-discovery dynamics · 0 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 the antisymmetric-Jacobian correction term to the nudged dynamics (AsymEP vs VF)feedforward CNN · CIFAR-10test accuracy (%): 10.00 -> 89.74Improved
Use Dyadic EP (doubled state space, energy on augmented space)feedforward CNN · CIFAR-10test accuracy (%): BP 90.66 vs Dyadic EP 90.69No clear effect
Use AsymEP instead of VF on a feedforward MNIST network1 hidden layer with 20 neurons · MNISTtest accuracy (%): 64.3 -> 92.7Improved
Increase structural asymmetry ratio r_str to 1 under VF (ablation)VF, 50 hidden neurons · MNISTtest accuracy (%): drops to 5 ± 3 (input-only), 8 ± 4 (all parameters)Hurt
Increase structural asymmetry ratio r_str under AsymEP (ablation)AsymEP, 50 hidden neurons · MNISTtest accuracy (%): 93.8 -> 94.9 (r_str 0 -> 0.875)No clear effect
Train all parameters including Jdyn rather than only Jin (ablation)AsymEP · MNIST (fixed asymmetry ratio)test accuracy (%)Improved
Train Jdyn in addition to Jin under VF (ablation)VF · MNIST (fixed asymmetry ratio)collapse point of r_str: collapse at r_str 0.5 -> 0.8Improved
Use AsymEP with asymmetric connectivity vs EP on symmetric networksCH dynamics, Fashion-MNIST · Fashion-MNIST (epoch 50)test accuracy (%): EP symmetric 84.30 -> AsymEP asymmetric 86.78Improved
Use AsymEP instead of VF on asymmetric and feedforward networksFashion-MNIST networks · Fashion-MNIST after 1 epochtest accuracy (%): on average 15% accuracy gainImproved
Increase depth of AsymEP network from 2 to 3 hidden layers of 500 (ablation)AsymEP · Fashion-MNISTtest accuracy (%): 86.41 -> 87.8Improved
Use AsymEP instead of EP and VF from a symmetric initializationcontinuous Hopfield network, one hidden layer · MNISTtest accuracyImproved

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