SOURCE-LINKED INTELLIGENCE

The Dynamics of Quasiregular Neural Learning

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Many learning problems combine a dominant regularity with systematic exceptions. Motivated by U-shaped learning in language acquisition, we study this interaction in controlled quasiregular regression problems where regular and exceptional solutions are explicitly known. Neural networks can partially acquire exceptions, subsequently regress toward the dominant regularity, and finally recover. This overregularization becomes substantially stronger when exceptions are rare, despite their early acquisition, but does not emerge equally across all regularities considered. Our results isolate a simp

Read original source ↗ Open in workspace

recordType

paper

region

Global