SOURCE-LINKED INTELLIGENCE

Introductory Notes on Learning$^2$

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Although machine learning can be used to predict the evolution of physical systems from data, a formulation that learns only the system state at each time leaves the temporal and dynamical structure of the solution to be resolved within a broad hypothesis space. We introduce Learning$^2$, a representation-level framework that structures this space by coupling a primary representation to a second representation through a known physical transformation. The resulting cross-representation constraint restricts the effective hypothesis space and provides an ante-hoc, physically interpretable criteri

Read original source ↗ Open in workspace

recordType

paper

region

Global