Layer Normalization
Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton submitted Layer Normalization on July 21, 2016. The paper proposed computing normalization statistics across the summed inputs to the neurons in a layer for a single training case, rather than across a mini-batch, and described the method as straightforward to apply to recurrent neural networks.
Historical classification
This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.
Why it matters
A documented neural-network normalization milestone introducing Layer Normalization as a training method distinct from mini-batch-dependent Batch Normalization.
People, organizations & technologies
PEOPLE
Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E. Hinton
TECHNOLOGIES
Layer Normalization, Deep neural networks, Recurrent neural networks
Evidence & verification
STATE
verified
CONFIDENCE
high
LAST VERIFIED
2026-09-11T16:07:15+08:00
The original arXiv record identifies the authors, July 21 2016 submission date, and the Layer Normalization method. Geoffrey Hinton's University of Toronto publication page and the author-hosted paper independently corroborate the paper, authors, 2016 publication context, and method description. The day-precision date is attached specifically to the arXiv submission milestone and is not asserted as a separate method-birth date. No geography, institutional affiliation, ancestry, influence, causality or relationships are inferred.
Sources
Trace the chronology
Record identity
LINEAiGE IDlayer-normalization-2016