Revision History
L2 Loss · 8 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected the object-detection section, which said Faster R-CNN trains box regression with L2 loss and called Smooth L1 a variant of L2 loss, and fixed a comparison row that credited L1 loss (rather than L1 regularization) with producing sparse coefficients (plus 13 minor fixes)
Version 8 · Nov 5, 2026, 12:15 PM
- Improve internal links (2026-10-13)
Version 6 · Oct 13, 2026, 10:00 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 02:59 PM
- Render formulas with LaTeX math notation
Version 4 · Jul 11, 2026, 09:27 PM