Skip to content
Learn AI by building
← World of AI

Neural Networks

Residual Connections

Shortcut paths that allow information to skip one or more network layers.

A residual connection adds the input of a block directly to its output. This gives information and gradients a shorter route through the network.

Residual connections made it practical to train very deep architectures by reducing degradation and vanishing-gradient problems. They are used in ResNets, transformers and many other modern networks.

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

Join any time · Build AI skills at your pace