Glossary · Phase 4 · Deep learning
Residual connection
A shortcut that adds a layer's input to its output, so information and gradients flow easily through deep networks.
Learn it properly
Residual connections · Skip connections that let gradients flow. About 30 minutes.
Other terms from the same lesson
- residual block: A layer that adds its result to its own input (x + f(x)), so the input always has a clean path through.
- residual stream: The running total that flows through a transformer: each layer reads it and adds its result back in, instead of replacing it.