Reference. On Layer Normalization in the Transformer Architecture [xiong2020layer]
Reference. On Layer Normalization in the Transformer Architecture [xiong2020layer]
@inproceedings{xiong2020layer,
title = {On Layer Normalization in the Transformer Architecture},
author = {Xiong, Ruibin and Yang, Yunchang and He, Di and Zheng, Kai and Zheng, Shuxin and Xing, Chen and Zhang, Huishuai and Lan, Yanyan and Wang, Liwei and Liu, Tie-Yan},
booktitle = {Proceedings of the 37th International Conference on Machine Learning},
year = {2020},
url = {https://arxiv.org/abs/2002.04745}
}