Skip to content

This is Kangqi's final project of DDA6202 Optimization Models and Methods in Machine Learning. My project is about the nomalization layer choice in transformer encoder. To this end, I utilized several tests proposed by previous researchers.

Notifications You must be signed in to change notification settings

KyleYu2003/The-Benefits-of-Normalization-Layers-in-Transformers

Repository files navigation

The-Benefits-of-Normalization-Layers-in-Transformers

This is Kangqi's final project of DDA6202 Optimization Models and Methods in Machine Learning. My project is about the nomalization layer choice in transformer encoder. To this end, I utilized several tests proposed by previous researchers.

About

This is Kangqi's final project of DDA6202 Optimization Models and Methods in Machine Learning. My project is about the nomalization layer choice in transformer encoder. To this end, I utilized several tests proposed by previous researchers.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages