On Layer Normalization in the Transformer Architecture.
https://arxiv.org/abs/2002.04745
@article{DBLP:journals/corr/abs-2002-04745,
author = {Ruibin Xiong and
Yunchang Yang and
Di He and
Kai Zheng and
Shuxin Zheng and
Chen Xing and
Huishuai Zhang and
Yanyan Lan and
Liwei Wang and
Tie{-}Yan Liu},
title = {On Layer Normalization in the Transformer Architecture},
journal = {CoRR},
volume = {abs/2002.04745},
year = {2020},
url = {https://arxiv.org/abs/2002.04745},
archivePrefix = {arXiv},
eprint = {2002.04745},
timestamp = {Fri, 14 Feb 2020 12:07:41 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-04745.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}