EVERYTHING AIAI engineering, made visual
Visual edition planned
Phase 19 · Lesson 59BuildPython1.5 h85 lessons in phase

Vision Transformer Encoder

Patches alone do not see. A 12-layer pre-LN transformer with 12 attention heads turns the sequence of patch tokens into a sequence of contextual tokens, with the CLS token pooling whole-image features in its final hidden state. This lesson is the engine room of every modern vision-language model.

Visual edition planned

This lesson isn’t interactive yet.

It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:

Part of Phase 19Capstone Projects. Use the previous / next cards below to keep browsing the phase.