AI Foundationspredict · compress · act

concepts → Algorithm

Algorithm

Backpropagation through time

timeless2 connectionsdraft

unroll a loop over time, then run backprop through the whole tape

Where it sits

The prism has six jobs across and eight layers down. Its primary cell islearn × L4. 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.

nothing comes first — this is a starting pointBackpropagation through timenothing depends on it yet — a leaf in the reading order

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

It is part of: Backpropagation.

Where to read it

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

21Memory in a Loopact 5 · The Connectionist Turn

Where it comes from

bookDeep LearningIan Goodfellow, Yoshua Bengio, Aaron Courville · 2016

Every connection

All 2 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Structure · 1
is part ofBackpropagationAlgorithm
Flow · 1
is used bySequence modelArchitecture

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.