AI Foundationspredict · compress · act

concepts → Quantity

Quantity

Entropy

timeless9 connections

the average surprise of a source, in bits

the formal statement
H (bits)
H(X) = −Σ p(x) log p(x)

Where it sits

The prism has six jobs across and eight layers down. Its primary cell ismeasure × L0. 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.

UncertaintyInformationEntropyCross-entropyKL divergenceMutual information

Before it: Uncertainty · Information

Unlocks: Cross-entropy · KL divergence · Mutual information

Where to read it

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

04Entropyact 1 · The Substrate

Where it comes from

paperA Mathematical Theory of CommunicationClaude E. Shannon · 1948

Every connection

All 9 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Order · 5
must come beforeCross-entropyObjective
must come beforeKL divergenceQuantity
must come beforeMutual informationQuantity
requiresUncertaintyProperty
requiresInformationQuantity
Flow · 3
is measured byBitQuantity
is used byCross-entropyObjective
is used byCompressionHeuristic
Contrast · 1
is dual toMutual informationQuantity

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.