Neural networks possess a propagation field of trajectories and Jacobians whose quality can be measured and optimized independently of endpoint loss, yielding better unseen-path generalization and reduced forgetting in continual learning.
Annalen der Physik , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Oblate effective deformation (D<1) and positive f(R,T) trace coupling systematically raise compact-star maximum masses and radii relative to spherical GR for GM1, MIT Bag, and polytropic equations of state.
citing papers explorer
-
The Propagation Field: A Geometric Substrate Theory of Deep Learning
Neural networks possess a propagation field of trajectories and Jacobians whose quality can be measured and optimized independently of endpoint loss, yielding better unseen-path generalization and reduced forgetting in continual learning.
-
Deformed Compact Objects in General Relativity and Modified Gravity
Oblate effective deformation (D<1) and positive f(R,T) trace coupling systematically raise compact-star maximum masses and radii relative to spherical GR for GM1, MIT Bag, and polytropic equations of state.