Concept detail
cancellation of pre-normalization
0 tagged videos · 1 connection videos · degree 0
Publication timeline
- 2026-091 video
Source videos
Observed neighbors
Scale-invariance of normalization
Scale-invariance permits dropping a redundant adjacent normalization in certain architectures.
1 source videos
Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip MakraduliRelated tagged insights
No core insights are tagged with this concept.