Prehistory — From Neural Networks to the TransformerJimmy Lei Ba, Jamie Ryan Kiros, Geoffrey HintonGeoffrey Hinton
Ba, Kiros and Hinton publish Layer Normalization on arXiv
Layer Normalization released on arXiv
Why it matters
Normalization that does not depend on the batch. Once the Transformer adopted it, it became a de facto basic component
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/1607.06450Added in Week 35, 2026 · See that week