A minimal embedding model shows representation collapse arises from frustrated samples through slow dynamics and is prevented by stop-gradient.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Thermodynamic networks using non-equilibrium steady states achieve universal function approximation when engineered with negative differential conductance, as shown in quantum dot and enzymatic examples for sine fitting and MNIST classification.
citing papers explorer
-
A Minimal Model of Representation Collapse: Frustration, Stop-Gradient, and Dynamics
A minimal embedding model shows representation collapse arises from frustrated samples through slow dynamics and is prevented by stop-gradient.
-
Thermodynamic Networks: Harnessing Non-Equilibrium Steady States for Computation
Thermodynamic networks using non-equilibrium steady states achieve universal function approximation when engineered with negative differential conductance, as shown in quantum dot and enzymatic examples for sine fitting and MNIST classification.