Revision History
Feedforward Neural Network (FFN) · 16 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 claim that SwiGLU adds about 15% more computation: Shazeer's GLU-variant FFNs keep parameters and computation equal to a standard FFN by shrinking the hidden dimension by a factor of 2/3 (plus 13 minor fixes)
Version 16 · Nov 4, 2026, 05:53 PM
- Update: fix a broken link inside the author name Jamie Ryan Kiros
Version 15 · Nov 2, 2026, 06:38 AM
- Improve internal links (2026-10-13)
Version 13 · Oct 13, 2026, 10:03 AM
- Added 6 contextual internal links
Version 12 · Jul 23, 2026, 03:01 PM
- Render formulas with LaTeX math notation
Version 11 · Jul 11, 2026, 10:31 PM