UnderstandingtheGeneralizationBenefitof NormalizationLayers: SharpnessReduction
–Neural Information Processing Systems
Previous ablation studies showedthatadding WD to normalized nets indeed leads to better generalization [126, 72, 125].
Neural Information Processing Systems
Feb-12-2026, 10:01:17 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe
- France > Hauts-de-France
- Germany (0.04)
- Latvia > Lubāna Municipality
- Lubāna (0.04)
- North America
- Canada > Ontario
- Toronto (0.04)
- United States > Minnesota
- Hennepin County > Minneapolis (0.14)
- Canada > Ontario
- Asia > Middle East
- Technology: