Revision History
Convolutional Layer · 10 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 TPU matrix-unit sizes, the AlphaFold Evoformer description (it uses attention, not convolutions), Deformable DETR (deformable attention, not deformable convolution), Swin Transformer mislabelled as a conv-attention hybrid, AlexNet's stem, the fully-connected versus locally-connected parameter comparison, and a false claim that the architecture table's figures all come from the original papers (plus 17 minor fixes)
Version 10 · Nov 2, 2026, 05:29 AM
- Update: added a video.
Version 9 · Nov 1, 2026, 08:28 AM
- Improve internal links (2026-10-13)
Version 7 · Oct 13, 2026, 10:02 AM
- Added 6 contextual internal links
Version 6 · Jul 23, 2026, 03:00 PM
- Render formulas with LaTeX math notation
Version 5 · Jul 11, 2026, 10:31 PM