发表机构
University of Groningen（格罗宁根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过受控准正则回归问题，揭示神经网络学习中的U形动态，即例外罕见时过度正则化增强，体现规律与例外的竞争。
AI 中文摘要
许多学习问题将主导规律性与系统性例外相结合。受语言习得中U形学习的启发，我们在受控的准正则回归问题中研究这种相互作用，其中正则解和例外解是明确已知的。神经网络能够部分习得例外，随后回归至主导规律，并最终恢复。当例外罕见时，这种过度正则化显著增强，尽管它们被早期习得，但并非在所有考虑的正则性中均等出现。我们的结果揭示了神经学习过程中规律性与例外之间一种简单的竞争形式。
英文摘要
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 simple form of competition between regularities and exceptions during neural learning.
