Use of Layer Normalization

tensorflow / tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Apache License 2.0

15.58k stars 3.51k forks source link

Open Andre1998Shuvam opened 2 years ago

Andre1998Shuvam commented 2 years ago

Hello! I would like to know why Layer Normalization and Residual connections have been used in the Transformer architecture.