Zenaique
Glossary · Architecture

Residual Connection

Also known as: Skip connection

Add the input of each sub-layer back to its output: the trick that lets us train 100+ layer transformers.

A skip connection that adds the input of a sub-layer directly to its output. Enables training very deep networks by ensuring gradient flow and identity-mapping capability. Used around every attention and MLP block in transformers.

In practice

If you don't know residuals you can't whiteboard a transformer block. Interview must-have.

Related topics

Questions that mention this term

Related terms