Revision History
Inductive bias · 5 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 Vision Transformers need hundreds of millions of pretraining images to match ResNets; the ViT paper puts the threshold at 14 million to 300 million images (ImageNet-21k or JFT-300M) (plus 2 minor fixes)
Version 5 · Nov 2, 2026, 11:59 AM
- Improve internal links (2026-10-13)
Version 4 · Oct 13, 2026, 10:19 AM
- Added 6 contextual internal links
Version 3 · Jul 23, 2026, 03:29 PM