AI Foundationspredict · compress · act

concepts → Mechanism

Mechanism

Word embedding

decade6 connections

words as coordinates, so that similar meanings sit near each other

Where it sits

The prism has six jobs across and eight layers down. Its primary cell isrepresent × L1. Hatched cells cannot exist — a GPU does not learn, an institution does not infer.

What must come first — and what it unlocks

Left to right is reading order, derived from the prerequisite_of edges. Nothing here is hand-ordered: the diagram is the graph.

VectorDistributional hypothesisWord embeddingAttention

Before it: Vector · Distributional hypothesis

Unlocks: Attention

What kind of thing it is — and what it is made of

Examples of it: word2vec.

It is made of: Embedding space.

Where to read it

The chapter that introduces it, and any chapter that uses it again.

22Words as Coordinatesact 5 · The Connectionist Turn

Where it comes from

paperEfficient Estimation of Word Representations in Vector SpaceTomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean · 2013

Every connection

All 6 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Structure · 2
has as a partEmbedding spacePhenomenon
has as an instanceword2vecAlgorithm
Order · 3
must come beforeAttentionMechanism
requiresVectorQuantity
requiresDistributional hypothesisHeuristic
Flow · 1

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 230 declared edges produce all 236 of these pages. Edit an edge and both endpoints change.