ConceptAI & ML
Encoder block
A modular component of the encoder consisting of a self-attention layer, a feedforward layer, layer norms, and residual connections.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Feedforward neural networks1Self-attention1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.