Fig.1

Concept

Transformer encoder

The Transformer encoder is the half of the original Transformer architecture that turns a sequence of input tokens into a sequence of context-aware vectors, one per token. Think of it like a stack of feature extractors, except instead of convolutions it uses…

The rest of “Transformer encoder” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library