AI Foundationspredict · compress · act

concepts → Quantity

Quantity

Sample complexity

timeless3 connections

how many examples it takes to learn, given how much capacity you allowed

the formal statement
n = O((VC + log(1/δ)) / ε²)

Where it sits

The prism has six jobs across and eight layers down. Its primary cell is measure × 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.

PAC learningVC dimensionSample complexitynothing depends on it yet — a leaf in the reading order

Before it: PAC learning · VC dimension

Where to read it

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

13How Much Data Is Enough?act IV · The Learning Floor

Where it comes from

paperLearnability and the Vapnik-Chervonenkis DimensionBlumer, Ehrenfeucht, Haussler, Warmuth · 1989
paperUnderstanding Deep Learning Requires Rethinking GeneralizationZhang, Bengio, Hardt, Recht, Vinyals · 2017

Every connection

All 3 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Order · 2
requiresPAC learningField
requiresVC dimensionQuantity
Flow · 1
measuresCapacityQuantity

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 521 declared edges produce all 340 of these pages. Edit an edge and both endpoints change.