"Understanding the Failure of Batch Normalization for Transformers in NLP."

Jiaxi Wang, Ji Wu, Lei Huang (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.05153

access: open

type: Informal or Other Publication

metadata version: 2024-08-14

a service of  Schloss Dagstuhl - Leibniz Center for Informatics